SU\G(𝔸)/K·U
Sign Up for free Log In

Author Description

Login to generate an author description

Ask a Question About This Mathematician

Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

2021-01-01
Prakhar Ganesh , Yao Chen , Xin Lou +6 more
Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and … Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and computation-intensive to suit low- capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted considerable research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.
View PDF Chat

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

2022-01-01
Prakhar Ganesh , Yao Chen , Yin Yang +2 more
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models … Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2×0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.
View PDF Chat

Abstractive Summarization of Spoken and Written Conversation.

2019-02-05
Prakhar Ganesh , Saket Dingliwal
Nowadays, lots of information is available in form of dialogues. We propose a novel abstractive summarization system for conversations. We use sequence tagging of utterances for identifying the discourse relations … Nowadays, lots of information is available in form of dialogues. We propose a novel abstractive summarization system for conversations. We use sequence tagging of utterances for identifying the discourse relations of the dialogue. After aptly capturing these relations in a paragraph, we feed it into an Attention-based pointer network to produce abstractive summaries. We obtain ROUGE-1, 2 F-scores similar to those of extractive summaries of various previous works.

On The Impact of Machine Learning Randomness on Group Fairness

2023-06-12
Prakhar Ganesh , Hongyan Chang , Martin Strobel +1 more
Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance between different training instances, which … Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance between different training instances, which makes them unreliable for empirical evaluation of fairness. What causes this high variance? We investigate the impact on group fairness of different sources of randomness in training neural networks. We show that the variance in group fairness measures is rooted in the high volatility of the learning process on under-represented groups. Further, we recognize the dominant source of randomness as the stochasticity of data order during training. Based on these findings, we show how one can control group-level accuracy (i.e., model fairness), with high efficiency and negligible impact on the model's overall performance, by simply changing the data order for a single epoch.
View PDF Chat

HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation

2022-01-17
Xinheng Liu , Yao Chen , Prakhar Ganesh +3 more
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic … Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as CPUs and DSPs, can be better utilized to carry out significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the compute throughput of a given underlying processing unit to process low-bitwidth quantized data inputs through novel bitwise parallel computation. We establish theoretical performance bounds using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit can deliver 128 binarized convolution operations (multiplications and additions) under one CPU instruction, and a single <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$27\times 18$</tex> DSP core can deliver eight convolution operations with 4-bit inputs in one cycle. We demonstrate the effectiveness of HiKonv on CPU and FPGA for both convolutional layers or a complete DNN model. For a convolutional layer quantized to 4-bit, HiKonv achieves a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$3.17\times$</tex> latency improvement over the baseline implementation using C++ on CPU. Compared to the DAC-SDC 2020 champion model for FPGA, HiKonv achieves a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2.37\times$</tex> : throughput improvement and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2.61\times$</tex> DSP efficiency improvement, respectively.
View PDF Chat

Deep Neural Networks in High Frequency Trading

2018-09-05
Prakhar Ganesh , Puneet Rakheja
The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. The main objective of this paper is … The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. The main objective of this paper is to propose a novel way of modeling the high frequency trading problem using Deep Neural Networks at its heart and to argue why Deep Learning methods can have a lot of potential in the field of High Frequency Trading. The paper goes on to analyze the model's performance based on it's prediction accuracy as well as prediction speed across full-day trading simulations.

Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization

2019-01-01
Prakhar Ganesh , Saket Dingliwal
Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting … Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.

VLSTM: Very Long Short-Term Memory Networks for High-Frequency Trading

2018-01-01
Prakhar Ganesh , Puneet Rakheja
Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field … Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field of financial trading. Financial markets have both long term and short term signals and thus a good predictive model in financial trading should be able to incorporate them together. One of the most sought after forms of electronic trading is high-frequency trading (HFT), typically known for microsecond sensitive changes, which results in a tremendous amount of data. LSTMs are one of the most capable variants of the RNN family that can handle long-term dependencies, but even they are not equipped to handle such long sequences of the order of thousands of data points like in HFT. We propose very-long short term memory networks, or VLSTMs, to deal with such extreme length sequences. We explore the importance of VLSTMs in the context of HFT. We compare our model on publicly available dataset and got a 3.14\% increase in F1-score over the existing state-of-the-art time-series forecasting models. We also show that our model has great parallelization potential, which is essential for practical purposes when trading on such markets.
View PDF Chat

Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization.

2019-02-05
Prakhar Ganesh , Saket Dingliwal
Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting … Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.

Literature Survey on Finding Influential Communities in Large Scale Networks

2019-01-01
Prakhar Ganesh , Saket Dingliwal , Rahul Agarwal
Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs … Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs is a problem of considerable interest as it often accounts for the functionality of the system. We aim to provide a thorough exposition of the topic, including the main elements of the problem, a brief introduction of the existing research for both disjoint and overlapping community search, the idea of influential communities, its implications and the current state of the art and finally provide some insight on possible directions for future research.
View PDF Chat

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

2021-01-01
Prakhar Ganesh , Yao Chen , Yin Yang +2 more
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models … Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2x0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.
View PDF Chat

The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity

2024-05-28
Prakhar Ganesh , Ihsan Ibrahim Daldaban , Ignacio Cofone +1 more
Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection. While this arbitrariness may seem inconsequential in expectation, its impact … Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection. While this arbitrariness may seem inconsequential in expectation, its impact on individuals can be severe. This paper explores various individual concerns stemming from multiplicity, including the effects of arbitrariness beyond final predictions, disparate arbitrariness for individuals belonging to protected groups, and the challenges associated with the arbitrariness of a single algorithmic system creating a monopoly across various contexts. It provides both an empirical examination of these concerns and a comprehensive analysis from the legal standpoint, addressing how these issues are perceived in the anti-discrimination law in Canada. We conclude the discussion with technical challenges in the current landscape of model multiplicity to meet legal requirements and the legal gap between current law and the implications of arbitrariness in model selection, highlighting relevant future research directions for both disciplines.
View PDF Chat

Literature Survey on Finding Influential Communities in Large Scale Networks.

2019-02-05
Prakhar Ganesh , Saket Dingliwal , Rahul Agarwal
Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs … Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs is a problem of considerable interest as it often accounts for the functionality of the system. We aim to provide a thorough exposition of the topic, including the main elements of the problem, a brief introduction of the existing research for both disjoint and overlapping community search, the idea of influential communities, its implications and the current state of the art and finally provide some insight on possible directions for future research.

VLSTM: Very Long Short-Term Memory Networks for High-Frequency Trading

2018-09-05
Prakhar Ganesh , Puneet Rakheja
Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field … Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field of financial trading. Financial markets have both long term and short term signals and thus a good predictive model in financial trading should be able to incorporate them together. One of the most sought after forms of electronic trading is high-frequency trading (HFT), typically known for microsecond sensitive changes, which results in a tremendous amount of data. LSTMs are one of the most capable variants of the RNN family that can handle long-term dependencies, but even they are not equipped to handle such long sequences of the order of thousands of data points like in HFT. We propose very-long short term memory networks, or VLSTMs, to deal with such extreme length sequences. We explore the importance of VLSTMs in the context of HFT. We compare our model on publicly available dataset and got a 3.14\% increase in F1-score over the existing state-of-the-art time-series forecasting models. We also show that our model has great parallelization potential, which is essential for practical purposes when trading on such markets.

Free Lunch for Co-Saliency Detection: Context Adjustment

2021-01-01
Lingdong Kong , Prakhar Ganesh , Tan Wang +3 more
We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level … We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level labeling, which has forced most recent works to rely instead on semantic segmentation or saliency detection datasets for training. However, the lack of proper co-saliency and the absence of multiple foreground objects in these datasets can lead to spurious variations and inherent biases learned by models. To tackle this, we introduce the idea of counterfactual training through context adjustment and propose a "cost-free" group-cut-paste (GCP) procedure to leverage off-the-shelf images and synthesize new samples. Following GCP, we collect a novel dataset called Context Adjustment Training (CAT). CAT consists of 33,500 images, which is four times larger than the current co-saliency detection datasets. All samples are automatically annotated with high-quality mask annotations, object categories, and edge maps. Extensive experiments on recent benchmarks are conducted, show that CAT can improve various state-of-the-art models by a large margin (5% ~ 25%). We hope that the scale, diversity, and quality of our dataset can benefit researchers in this area and beyond. Our dataset will be publicly accessible through our project page.

HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation

2021-01-01
Xinheng Liu , Yao Chen , Prakhar Ganesh +3 more
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic … Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as CPUs and DSPs, can be better utilized to carry out significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the compute throughput of a given underlying processing unit to process low-bitwidth quantized data inputs through novel bit-wise parallel computation. We establish theoretical performance bounds using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit can deliver 128 binarized convolution operations (multiplications and additions) under one CPU instruction, and a single 27x18 DSP core can deliver eight convolution operations with 4-bit inputs in one cycle. We demonstrate the effectiveness of HiKonv on CPU and FPGA for both convolutional layers or a complete DNN model. For a convolutional layer quantized to 4-bit, HiKonv achieves a 3.17x latency improvement over the baseline implementation using C++ on CPU. Compared to the DAC-SDC 2020 champion model for FPGA, HiKonv achieves a 2.37x throughput improvement and 2.61x DSP efficiency improvement, respectively.
View PDF Chat

An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification

2023-01-01
Prakhar Ganesh
Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying … Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This multiplicity presents a significant challenge and necessitates additional specifications in model selection to prevent unexpected failures during deployment. While prior studies have examined these concerns, they focus on individual metrics in isolation, making it difficult to obtain a comprehensive view of multiplicity in trustworthy machine learning. Our work stands out by offering a one-stop empirical benchmark of multiplicity across various dimensions of model design and its impact on a diverse set of trustworthy metrics. In this work, we establish a consistent language for studying model multiplicity by translating several trustworthy metrics into accuracy under appropriate interventions. We also develop a framework, which we call multiplicity sheets, to benchmark multiplicity in various scenarios. We demonstrate the advantages of our setup through a case study in image classification and provide actionable insights into the impact and trends of different hyperparameters on model multiplicity. Finally, we show that multiplicity persists in deep learning models even after enforcing additional specifications during model selection, highlighting the severity of over-parameterization. The concerns of under-specification thus remain, and we seek to promote a more comprehensive discussion of multiplicity in trustworthy machine learning.

An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification

2024-01-03
Prakhar Ganesh
Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying … Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This multiplicity presents a significant challenge and necessitates additional specifications in model selection to prevent unexpected failures during deployment. While prior studies have examined these concerns, they focus on individual metrics in isolation, making it difficult to obtain a comprehensive view of multiplicity in trustworthy machine learning. Our work stands out by offering a one-stop empirical benchmark of multiplicity across various dimensions of model design and its impact on a diverse set of trustworthy metrics.In this work, we establish a consistent language for studying model multiplicity by translating several trustworthy metrics into accuracy under appropriate interventions. We also develop a framework, which we call multiplicity sheets, to benchmark multiplicity in various scenarios. We demonstrate the advantages of our setup through a case study in image classification and provide actionable insights into the impact and trends of different hyperparameters on model multiplicity. Finally, we show that multiplicity persists in deep learning models even after enforcing additional specifications during model selection, highlighting the severity of over-parameterization. The concerns of under-specification thus remain, and we seek to promote a more comprehensive discussion of multiplicity in trustworthy machine learning.
View PDF Chat

The Data Minimization Principle in Machine Learning

2024-05-29
Prakhar Ganesh , Cuong Tran , Reza Shokri +1 more
The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design … The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design principles, data minimization has been endorsed by various global data protection regulations. However, its practical implementation remains a challenge due to the lack of a rigorous formulation. This paper addresses this gap and introduces an optimization framework for data minimization based on its legal definitions. It then adapts several optimization algorithms to perform data minimization and conducts a comprehensive evaluation in terms of their compliance with minimization objectives as well as their impact on user privacy. Our analysis underscores the mismatch between the privacy expectations of data minimization and the actual privacy benefits, emphasizing the need for approaches that account for multiple facets of real-world privacy risks.
View PDF Chat

Towards More Realistic Extraction Attacks: An Adversarial Perspective

2024-07-02
Yash More , Prakhar Ganesh , Golnoosh Farnadi
Language models are prone to memorizing large parts of their training data, making them vulnerable to extraction attacks. Existing research on these attacks remains limited in scope, often studying isolated … Language models are prone to memorizing large parts of their training data, making them vulnerable to extraction attacks. Existing research on these attacks remains limited in scope, often studying isolated trends rather than the real-world interactions with these models. In this paper, we revisit extraction attacks from an adversarial perspective, exploiting the brittleness of language models. We find significant churn in extraction attack trends, i.e., even minor, unintuitive changes to the prompt, or targeting smaller models and older checkpoints, can exacerbate the risks of extraction by up to $2-4 \times$. Moreover, relying solely on the widely accepted verbatim match underestimates the extent of extracted information, and we provide various alternatives to more accurately capture the true risks of extraction. We conclude our discussion with data deduplication, a commonly suggested mitigation strategy, and find that while it addresses some memorization concerns, it remains vulnerable to the same escalation of extraction risks against a real-world adversary. Our findings highlight the necessity of acknowledging an adversary's true capabilities to avoid underestimating extraction risks.
View PDF Chat

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

2024-11-17
Prakhar Ganesh , Usman Gohar , Chang Lu +1 more
With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the best method. These benchmarking efforts … With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.
View PDF Chat

The Curious Case of Arbitrariness in Machine Learning

2025-01-24
Prakhar Ganesh , Afaf Taïk , Golnoosh Farnadi
Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has … Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is multiplicity-the study of arbitrariness across a set of "good models", i.e., those likely to be deployed in practice. In this work, we systemize the literature on multiplicity by: (a) formalizing the terminology around model design choices and their contribution to arbitrariness, (b) expanding the definition of multiplicity to incorporate underrepresented forms beyond just predictions and explanations, (c) clarifying the distinction between multiplicity and other traditional lenses of arbitrariness, i.e., uncertainty and variance, and (d) distilling the benefits and potential risks of multiplicity into overarching trends, situating it within the broader landscape of responsible AI. We conclude by identifying open research questions and highlighting emerging trends in this young but rapidly growing area of research.
View PDF Chat

The Curious Case of Arbitrariness in Machine Learning

2025-01-24
Prakhar Ganesh , Afaf Taïk , Golnoosh Farnadi
Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has … Algorithmic modelling relies on limited information in data to extrapolate outcomes for unseen scenarios, often embedding an element of arbitrariness in its decisions. A perspective on this arbitrariness that has recently gained interest is multiplicity-the study of arbitrariness across a set of "good models", i.e., those likely to be deployed in practice. In this work, we systemize the literature on multiplicity by: (a) formalizing the terminology around model design choices and their contribution to arbitrariness, (b) expanding the definition of multiplicity to incorporate underrepresented forms beyond just predictions and explanations, (c) clarifying the distinction between multiplicity and other traditional lenses of arbitrariness, i.e., uncertainty and variance, and (d) distilling the benefits and potential risks of multiplicity into overarching trends, situating it within the broader landscape of responsible AI. We conclude by identifying open research questions and highlighting emerging trends in this young but rapidly growing area of research.
View PDF Chat

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

2024-11-17
Prakhar Ganesh , Usman Gohar , Chang Lu +1 more
With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the best method. These benchmarking efforts … With fairness concerns gaining significant attention in Machine Learning (ML), several bias mitigation techniques have been proposed, often compared against each other to find the best method. These benchmarking efforts tend to use a common setup for evaluation under the assumption that providing a uniform environment ensures a fair comparison. However, bias mitigation techniques are sensitive to hyperparameter choices, random seeds, feature selection, etc., meaning that comparison on just one setting can unfairly favour certain algorithms. In this work, we show significant variance in fairness achieved by several algorithms and the influence of the learning pipeline on fairness scores. We highlight that most bias mitigation techniques can achieve comparable performance, given the freedom to perform hyperparameter optimization, suggesting that the choice of the evaluation parameters-rather than the mitigation technique itself-can sometimes create the perceived superiority of one method over another. We hope our work encourages future research on how various choices in the lifecycle of developing an algorithm impact fairness, and trends that guide the selection of appropriate algorithms.
View PDF Chat

Towards More Realistic Extraction Attacks: An Adversarial Perspective

2024-07-02
Yash More , Prakhar Ganesh , Golnoosh Farnadi
Language models are prone to memorizing large parts of their training data, making them vulnerable to extraction attacks. Existing research on these attacks remains limited in scope, often studying isolated … Language models are prone to memorizing large parts of their training data, making them vulnerable to extraction attacks. Existing research on these attacks remains limited in scope, often studying isolated trends rather than the real-world interactions with these models. In this paper, we revisit extraction attacks from an adversarial perspective, exploiting the brittleness of language models. We find significant churn in extraction attack trends, i.e., even minor, unintuitive changes to the prompt, or targeting smaller models and older checkpoints, can exacerbate the risks of extraction by up to $2-4 \times$. Moreover, relying solely on the widely accepted verbatim match underestimates the extent of extracted information, and we provide various alternatives to more accurately capture the true risks of extraction. We conclude our discussion with data deduplication, a commonly suggested mitigation strategy, and find that while it addresses some memorization concerns, it remains vulnerable to the same escalation of extraction risks against a real-world adversary. Our findings highlight the necessity of acknowledging an adversary's true capabilities to avoid underestimating extraction risks.
View PDF Chat

The Data Minimization Principle in Machine Learning

2024-05-29
Prakhar Ganesh , Cuong Tran , Reza Shokri +1 more
The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design … The principle of data minimization aims to reduce the amount of data collected, processed or retained to minimize the potential for misuse, unauthorized access, or data breaches. Rooted in privacy-by-design principles, data minimization has been endorsed by various global data protection regulations. However, its practical implementation remains a challenge due to the lack of a rigorous formulation. This paper addresses this gap and introduces an optimization framework for data minimization based on its legal definitions. It then adapts several optimization algorithms to perform data minimization and conducts a comprehensive evaluation in terms of their compliance with minimization objectives as well as their impact on user privacy. Our analysis underscores the mismatch between the privacy expectations of data minimization and the actual privacy benefits, emphasizing the need for approaches that account for multiple facets of real-world privacy risks.
View PDF Chat

The Cost of Arbitrariness for Individuals: Examining the Legal and Technical Challenges of Model Multiplicity

2024-05-28
Prakhar Ganesh , Ihsan Ibrahim Daldaban , Ignacio Cofone +1 more
Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection. While this arbitrariness may seem inconsequential in expectation, its impact … Model multiplicity, the phenomenon where multiple models achieve similar performance despite different underlying learned functions, introduces arbitrariness in model selection. While this arbitrariness may seem inconsequential in expectation, its impact on individuals can be severe. This paper explores various individual concerns stemming from multiplicity, including the effects of arbitrariness beyond final predictions, disparate arbitrariness for individuals belonging to protected groups, and the challenges associated with the arbitrariness of a single algorithmic system creating a monopoly across various contexts. It provides both an empirical examination of these concerns and a comprehensive analysis from the legal standpoint, addressing how these issues are perceived in the anti-discrimination law in Canada. We conclude the discussion with technical challenges in the current landscape of model multiplicity to meet legal requirements and the legal gap between current law and the implications of arbitrariness in model selection, highlighting relevant future research directions for both disciplines.
View PDF Chat

An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification

2024-01-03
Prakhar Ganesh
Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying … Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This multiplicity presents a significant challenge and necessitates additional specifications in model selection to prevent unexpected failures during deployment. While prior studies have examined these concerns, they focus on individual metrics in isolation, making it difficult to obtain a comprehensive view of multiplicity in trustworthy machine learning. Our work stands out by offering a one-stop empirical benchmark of multiplicity across various dimensions of model design and its impact on a diverse set of trustworthy metrics.In this work, we establish a consistent language for studying model multiplicity by translating several trustworthy metrics into accuracy under appropriate interventions. We also develop a framework, which we call multiplicity sheets, to benchmark multiplicity in various scenarios. We demonstrate the advantages of our setup through a case study in image classification and provide actionable insights into the impact and trends of different hyperparameters on model multiplicity. Finally, we show that multiplicity persists in deep learning models even after enforcing additional specifications during model selection, highlighting the severity of over-parameterization. The concerns of under-specification thus remain, and we seek to promote a more comprehensive discussion of multiplicity in trustworthy machine learning.
View PDF Chat

On The Impact of Machine Learning Randomness on Group Fairness

2023-06-12
Prakhar Ganesh , Hongyan Chang , Martin Strobel +1 more
Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance between different training instances, which … Statistical measures for group fairness in machine learning reflect the gap in performance of algorithms across different groups. These measures, however, exhibit a high variance between different training instances, which makes them unreliable for empirical evaluation of fairness. What causes this high variance? We investigate the impact on group fairness of different sources of randomness in training neural networks. We show that the variance in group fairness measures is rooted in the high volatility of the learning process on under-represented groups. Further, we recognize the dominant source of randomness as the stochasticity of data order during training. Based on these findings, we show how one can control group-level accuracy (i.e., model fairness), with high efficiency and negligible impact on the model's overall performance, by simply changing the data order for a single epoch.
View PDF Chat

An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification

2023-01-01
Prakhar Ganesh
Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying … Deep learning models have proven to be highly successful. Yet, their over-parameterization gives rise to model multiplicity, a phenomenon in which multiple models achieve similar performance but exhibit distinct underlying behaviours. This multiplicity presents a significant challenge and necessitates additional specifications in model selection to prevent unexpected failures during deployment. While prior studies have examined these concerns, they focus on individual metrics in isolation, making it difficult to obtain a comprehensive view of multiplicity in trustworthy machine learning. Our work stands out by offering a one-stop empirical benchmark of multiplicity across various dimensions of model design and its impact on a diverse set of trustworthy metrics. In this work, we establish a consistent language for studying model multiplicity by translating several trustworthy metrics into accuracy under appropriate interventions. We also develop a framework, which we call multiplicity sheets, to benchmark multiplicity in various scenarios. We demonstrate the advantages of our setup through a case study in image classification and provide actionable insights into the impact and trends of different hyperparameters on model multiplicity. Finally, we show that multiplicity persists in deep learning models even after enforcing additional specifications during model selection, highlighting the severity of over-parameterization. The concerns of under-specification thus remain, and we seek to promote a more comprehensive discussion of multiplicity in trustworthy machine learning.

HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation

2022-01-17
Xinheng Liu , Yao Chen , Prakhar Ganesh +3 more
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic … Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as CPUs and DSPs, can be better utilized to carry out significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the compute throughput of a given underlying processing unit to process low-bitwidth quantized data inputs through novel bitwise parallel computation. We establish theoretical performance bounds using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit can deliver 128 binarized convolution operations (multiplications and additions) under one CPU instruction, and a single <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$27\times 18$</tex> DSP core can deliver eight convolution operations with 4-bit inputs in one cycle. We demonstrate the effectiveness of HiKonv on CPU and FPGA for both convolutional layers or a complete DNN model. For a convolutional layer quantized to 4-bit, HiKonv achieves a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$3.17\times$</tex> latency improvement over the baseline implementation using C++ on CPU. Compared to the DAC-SDC 2020 champion model for FPGA, HiKonv achieves a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2.37\times$</tex> : throughput improvement and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$2.61\times$</tex> DSP efficiency improvement, respectively.
View PDF Chat

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

2022-01-01
Prakhar Ganesh , Yao Chen , Yin Yang +2 more
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models … Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2×0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.
View PDF Chat

Free Lunch for Co-Saliency Detection: Context Adjustment

2021-01-01
Lingdong Kong , Prakhar Ganesh , Tan Wang +3 more
We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level … We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level labeling, which has forced most recent works to rely instead on semantic segmentation or saliency detection datasets for training. However, the lack of proper co-saliency and the absence of multiple foreground objects in these datasets can lead to spurious variations and inherent biases learned by models. To tackle this, we introduce the idea of counterfactual training through context adjustment and propose a "cost-free" group-cut-paste (GCP) procedure to leverage off-the-shelf images and synthesize new samples. Following GCP, we collect a novel dataset called Context Adjustment Training (CAT). CAT consists of 33,500 images, which is four times larger than the current co-saliency detection datasets. All samples are automatically annotated with high-quality mask annotations, object categories, and edge maps. Extensive experiments on recent benchmarks are conducted, show that CAT can improve various state-of-the-art models by a large margin (5% ~ 25%). We hope that the scale, diversity, and quality of our dataset can benefit researchers in this area and beyond. Our dataset will be publicly accessible through our project page.

Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

2021-01-01
Prakhar Ganesh , Yao Chen , Xin Lou +6 more
Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and … Abstract Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and thus are too resource- hungry and computation-intensive to suit low- capability devices or applications with strict latency requirements. One potential remedy for this is model compression, which has attracted considerable research attention. Here, we summarize the research in compressing Transformers, focusing on the especially popular BERT model. In particular, we survey the state of the art in compression for BERT, we clarify the current best practices for compressing large-scale Transformer models, and we provide insights into the workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving lightweight, accurate, and generic NLP models.
View PDF Chat

YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs

2021-01-01
Prakhar Ganesh , Yao Chen , Yin Yang +2 more
Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models … Performance of object detection models has been growing rapidly on two major fronts, model accuracy and efficiency. However, in order to map deep neural network (DNN) based object detection models to edge devices, one typically needs to compress such models significantly, thus compromising the model accuracy. In this paper, we propose a novel edge GPU friendly module for multi-scale feature interaction by exploiting missing combinatorial connections between various feature scales in existing state-of-the-art methods. Additionally, we propose a novel transfer learning backbone adoption inspired by the changing translational information flow across various tasks, designed to complement our feature interaction module and together improve both accuracy as well as execution speed on various edge GPU devices available in the market. For instance, YOLO-ReT with MobileNetV2x0.75 backbone runs real-time on Jetson Nano, and achieves 68.75 mAP on Pascal VOC and 34.91 mAP on COCO, beating its peers by 3.05 mAP and 0.91 mAP respectively, while executing faster by 3.05 FPS. Furthermore, introducing our multi-scale feature interaction module in YOLOv4-tiny and YOLOv4-tiny (3l) improves their performance to 41.5 and 48.1 mAP respectively on COCO, outperforming the original versions by 1.3 and 0.9 mAP.
View PDF Chat

HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation

2021-01-01
Xinheng Liu , Yao Chen , Prakhar Ganesh +3 more
Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic … Quantization for Convolutional Neural Network (CNN) has shown significant progress with the intention of reducing the cost of computation and storage with low-bitwidth data inputs. There are, however, no systematic studies on how an existing full-bitwidth processing unit, such as CPUs and DSPs, can be better utilized to carry out significantly higher computation throughput for convolution under various quantized bitwidths. In this study, we propose HiKonv, a unified solution that maximizes the compute throughput of a given underlying processing unit to process low-bitwidth quantized data inputs through novel bit-wise parallel computation. We establish theoretical performance bounds using a full-bitwidth multiplier for highly parallelized low-bitwidth convolution, and demonstrate new breakthroughs for high-performance computing in this critical domain. For example, a single 32-bit processing unit can deliver 128 binarized convolution operations (multiplications and additions) under one CPU instruction, and a single 27x18 DSP core can deliver eight convolution operations with 4-bit inputs in one cycle. We demonstrate the effectiveness of HiKonv on CPU and FPGA for both convolutional layers or a complete DNN model. For a convolutional layer quantized to 4-bit, HiKonv achieves a 3.17x latency improvement over the baseline implementation using C++ on CPU. Compared to the DAC-SDC 2020 champion model for FPGA, HiKonv achieves a 2.37x throughput improvement and 2.61x DSP efficiency improvement, respectively.
View PDF Chat

Literature Survey on Finding Influential Communities in Large Scale Networks.

2019-02-05
Prakhar Ganesh , Saket Dingliwal , Rahul Agarwal
Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs … Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs is a problem of considerable interest as it often accounts for the functionality of the system. We aim to provide a thorough exposition of the topic, including the main elements of the problem, a brief introduction of the existing research for both disjoint and overlapping community search, the idea of influential communities, its implications and the current state of the art and finally provide some insight on possible directions for future research.

Abstractive Summarization of Spoken and Written Conversation.

2019-02-05
Prakhar Ganesh , Saket Dingliwal
Nowadays, lots of information is available in form of dialogues. We propose a novel abstractive summarization system for conversations. We use sequence tagging of utterances for identifying the discourse relations … Nowadays, lots of information is available in form of dialogues. We propose a novel abstractive summarization system for conversations. We use sequence tagging of utterances for identifying the discourse relations of the dialogue. After aptly capturing these relations in a paragraph, we feed it into an Attention-based pointer network to produce abstractive summaries. We obtain ROUGE-1, 2 F-scores similar to those of extractive summaries of various previous works.

Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization.

2019-02-05
Prakhar Ganesh , Saket Dingliwal
Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting … Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.

Restructuring Conversations using Discourse Relations for Zero-shot Abstractive Dialogue Summarization

2019-01-01
Prakhar Ganesh , Saket Dingliwal
Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting … Dialogue summarization is a challenging problem due to the informal and unstructured nature of conversational data. Recent advances in abstractive summarization have been focused on data-hungry neural models and adapting these models to a new domain requires the availability of domain-specific manually annotated corpus created by linguistic experts. We propose a zero-shot abstractive dialogue summarization method that uses discourse relations to provide structure to conversations, and then uses an out-of-the-box document summarization model to create final summaries. Experiments on the AMI and ICSI meeting corpus, with document summarization models like PGN and BART, shows that our method improves the ROGUE score by up to 3 points, and even performs competitively against other state-of-the-art methods.

Literature Survey on Finding Influential Communities in Large Scale Networks

2019-01-01
Prakhar Ganesh , Saket Dingliwal , Rahul Agarwal
Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs … Community or modular structure is considered to be a significant property of large scale real-world graphs such as social or information networks. Detecting influential clusters or communities in these graphs is a problem of considerable interest as it often accounts for the functionality of the system. We aim to provide a thorough exposition of the topic, including the main elements of the problem, a brief introduction of the existing research for both disjoint and overlapping community search, the idea of influential communities, its implications and the current state of the art and finally provide some insight on possible directions for future research.
View PDF Chat

Deep Neural Networks in High Frequency Trading

2018-09-05
Prakhar Ganesh , Puneet Rakheja
The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. The main objective of this paper is … The ability to give precise and fast prediction for the price movement of stocks is the key to profitability in High Frequency Trading. The main objective of this paper is to propose a novel way of modeling the high frequency trading problem using Deep Neural Networks at its heart and to argue why Deep Learning methods can have a lot of potential in the field of High Frequency Trading. The paper goes on to analyze the model's performance based on it's prediction accuracy as well as prediction speed across full-day trading simulations.

VLSTM: Very Long Short-Term Memory Networks for High-Frequency Trading

2018-09-05
Prakhar Ganesh , Puneet Rakheja
Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field … Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field of financial trading. Financial markets have both long term and short term signals and thus a good predictive model in financial trading should be able to incorporate them together. One of the most sought after forms of electronic trading is high-frequency trading (HFT), typically known for microsecond sensitive changes, which results in a tremendous amount of data. LSTMs are one of the most capable variants of the RNN family that can handle long-term dependencies, but even they are not equipped to handle such long sequences of the order of thousands of data points like in HFT. We propose very-long short term memory networks, or VLSTMs, to deal with such extreme length sequences. We explore the importance of VLSTMs in the context of HFT. We compare our model on publicly available dataset and got a 3.14\% increase in F1-score over the existing state-of-the-art time-series forecasting models. We also show that our model has great parallelization potential, which is essential for practical purposes when trading on such markets.

VLSTM: Very Long Short-Term Memory Networks for High-Frequency Trading

2018-01-01
Prakhar Ganesh , Puneet Rakheja
Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field … Financial trading is at the forefront of time-series analysis, and has grown hand-in-hand with it. The advent of electronic trading has allowed complex machine learning solutions to enter the field of financial trading. Financial markets have both long term and short term signals and thus a good predictive model in financial trading should be able to incorporate them together. One of the most sought after forms of electronic trading is high-frequency trading (HFT), typically known for microsecond sensitive changes, which results in a tremendous amount of data. LSTMs are one of the most capable variants of the RNN family that can handle long-term dependencies, but even they are not equipped to handle such long sequences of the order of thousands of data points like in HFT. We propose very-long short term memory networks, or VLSTMs, to deal with such extreme length sequences. We explore the importance of VLSTMs in the context of HFT. We compare our model on publicly available dataset and got a 3.14\% increase in F1-score over the existing state-of-the-art time-series forecasting models. We also show that our model has great parallelization potential, which is essential for practical purposes when trading on such markets.
View PDF Chat
Coauthor Papers Together
Yao Chen 5
Saket Dingliwal 5
Deming Chen 5
Golnoosh Farnadi 4
Puneet Rakheja 3
Marianne Winslett 3
Junhao Pan 2
Reza Shokri 2
Xinheng Liu 2
Jinjun Xiong 2
Lingdong Kong 1
Usman Gohar 1
Afaf Taïk 1
Hongyan Chang 1
Le Zhang 1
Tan Wang 1
Chang Lu 1
Junhao Liu 1
Xin Lou 1
Rahul Agarwal 1
Mohammad Ali Khan 1
Rahul Agarwal 1
Ihsan Ibrahim Daldaban 1
Cuong Tran 1
Ignacio Cofone 1
Preslav Nakov 1
Yin Yang 1
Yash More 1
Yin Yang 1
Hassan Sajjad 1
Yao Chen 1
Ferdinando Fioretto 1
Yin Yang 1
Martin Strobel 1