Eran Malach

Generating author description...

All published works

Action	Title	Year	Authors
+ PDF Chat	Loss-to-Loss Prediction: Scaling Laws for All Datasets	2024	David Brandfonbrener Nikhil Anand Nikhil Vyas Eran Malach Sham M. Kakade
+ PDF Chat	Mixture of Parrots: Experts improve memorization more than reasoning	2024	Samy Jelassi Clara Mohri David Brandfonbrener Alex Gu Nikhil Vyas Nikhil Anand David Alvarez-Melis Yuanzhi Li Sham M. Kakade Eran Malach
+ PDF Chat	LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks	2024	Akshara Prabhakar Yuanzhi Li Karthik Narasimhan Sham M. Kakade Eran Malach Samy Jelassi
+ PDF Chat	On the Power of Decision Trees in Auto-Regressive Language Modeling	2024	Ye-Hua Gan Tomer Galanti Tomaso Poggio Eran Malach
+ PDF Chat	Universal Length Generalization with Turing Programs	2024	Kaiying Hou David Brandfonbrener Sham M. Kakade Samy Jelassi Eran Malach
+ PDF Chat	A New Perspective on Shampoo's Preconditioner	2024	Depen Morwani Itai Shapira Nikhil Vyas Eran Malach Sham M. Kakade Lucas Janson
+ PDF Chat	Transcendence: Generative Models Can Outperform The Experts That Train Them	2024	Wei Zhang Vincent Zhu Naomi Saphra Anat Kleiman Benjamin Edelman Milind Tambe Sham M. Kakade Eran Malach
+ PDF Chat	The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains	2024	Benjamin Edelman Ezra Edelman Surbhi Goel Eran Malach Nikolaos Tsilivis
+ PDF Chat	Repeat After Me: Transformers are Better than State Space Models at Copying	2024	Samy Jelassi David Brandfonbrener Sham M. Kakade Eran Malach
+	Less is More: Selective Layer Finetuning with SubTuning	2023	Gal Kaplun Andrey Gurevich Tal Swisa Mazor David Shai Shalev‐Shwartz Eran Malach
+	Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck	2023	Benjamin Edelman Surbhi Goel Sham M. Kakade Eran Malach Cyril Zhang
+	Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD	2023	E. Livne Gal Kaplun Eran Malach Shai Shalev-Schwatz
+	Auto-Regressive Next-Token Predictors are Universal Learners	2023	Eran Malach
+	Knowledge Distillation: Bad Models Can Be Good Role Models	2022	Gal Kaplun Eran Malach Preetum Nakkiran Shai Shalev‐Shwartz
+	Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit	2022	Boaz Barak Benjamin Edelman Surbhi Goel Sham M. Kakade Eran Malach Cyril Zhang
+	On the Power of Differentiable Learning versus PAC and SQ Learning	2021	Emmanuel Abbé Pritish Kamath Eran Malach Colin Sandon Nathan Srebro
+	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks	2021	Eran Malach Gilad Yehudai Shai Shalev‐Shwartz Ohad Shamir
+	Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels	2021	Eran Malach Pritish Kamath Emmanuel Abbé Nathan Srebro
+	The Connection Between Approximation, Depth Separation and Learnability in Neural Networks	2021	Eran Malach Gilad Yehudai Shai Shalev‐Shwartz Ohad Shamir
+	On the Power of Differentiable Learning versus PAC and SQ Learning	2021	Emmanuel Abbé Pritish Kamath Eran Malach Colin Sandon Nathan Srebro
+	Learning Parities with Neural Networks	2020	Amit Daniely Eran Malach
+	Proving the Lottery Ticket Hypothesis: Pruning is All You Need	2020	Eran Malach Gilad Yehudai Shai Shalev‐Shwartz Ohad Shamir
+	When Hardness of Approximation Meets Hardness of Learning	2020	Eran Malach Shai Shalev‐Shwartz
+	Computational Separation Between Convolutional and Fully-Connected Networks	2020	Eran Malach Shai Shalev‐Shwartz
+	Learning Parities with Neural Networks	2020	Amit Daniely Eran Malach
+	Proving the Lottery Ticket Hypothesis: Pruning is All You Need	2020	Eran Malach Gilad Yehudai Shai Shalev‐Shwartz Ohad Shamir
+	Is Deeper Better only when Shallow is Good?	2019	Eran Malach Shai Shalev‐Shwartz
+	Decoupling Gating from Linearity	2019	Jonathan Fiat Eran Malach Shai Shalev‐Shwartz
+	ID3 Learns Juntas for Smoothed Product Distributions	2019	Alon Brutzkus Amit Daniely Eran Malach
+	On the Optimality of Trees Generated by ID3	2019	Alon Brutzkus Amit Daniely Eran Malach
+	Learning Boolean Circuits with Neural Networks	2019	Eran Malach Shai Shalev‐Shwartz
+	A Provably Correct Algorithm for Deep Learning that Actually Works	2018	Eran Malach Shai Shalev‐Shwartz
+	SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data	2017	Alon Brutzkus Amir Globerson Eran Malach Shai Shalev‐Shwartz
+	Decoupling "when to update" from "how to update"	2017	Eran Malach Shai Shalev‐Shwartz
+	SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data	2017	Alon Brutzkus Amir Globerson Eran Malach Shai Shalev‐Shwartz

Common Coauthors

Coauthor	Papers Together
Shai Shalev‐Shwartz	15
Sham M. Kakade	9
Benjamin Edelman	4
Gilad Yehudai	4
Ohad Shamir	4
Amit Daniely	4
Alon Brutzkus	4
Samy Jelassi	4
David Brandfonbrener	4
Nikhil Vyas	3
Gal Kaplun	3
Surbhi Goel	3
Emmanuel Abbé	3
Nathan Srebro	3
Pritish Kamath	3
Amir Globerson	2
Colin Sandon	2
Nikhil Anand	2
Cyril Zhang	2
Jonathan Fiat	1
Alex Gu	1
Yuanzhi Li	1
Ye-Hua Gan	1
Mazor David	1
Akshara Prabhakar	1
Naomi Saphra	1
Depen Morwani	1
Shai Shalev-Schwatz	1
Itai Shapira	1
Lucas Janson	1
Wei Zhang	1
Kaiying Hou	1
Yuanzhi Li	1
Milind Tambe	1
Ezra Edelman	1
Tomaso Poggio	1
Boaz Barak	1
Preetum Nakkiran	1
Vincent Zhu	1
David Alvarez-Melis	1
Andrey Gurevich	1
E. Livne	1
Clara Mohri	1
Anat Kleiman	1
Tal Swisa	1
Nikolaos Tsilivis	1
Karthik Narasimhan	1
Tomer Galanti	1

Commonly Cited References

Action	Title	Year	Authors	# of times referenced
+	Gradient Descent Provably Optimizes Over-parameterized Neural Networks	2018	Simon S. Du Xiyu Zhai Barnabás Póczos Aarti Singh	7
+	Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks	2019	Sanjeev Arora Simon S. Du Wei Hu Zhiyuan Li Ruosong Wang	6
+	SGD Learns the Conjugate Kernel Class of the Network	2017	Amit Daniely	5
+	A Convergence Theory for Deep Learning via Over-Parameterization	2018	Zeyuan Allen-Zhu Yuanzhi Li Zhao Song	5
+	Learning Parities with Neural Networks	2020	Amit Daniely Eran Malach	5
+	On the Power and Limitations of Random Features for Understanding Neural Networks	2019	Gilad Yehudai Ohad Shamir	5
+	Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers	2018	Zeyuan Allen-Zhu Yuanzhi Li Yingyu Liang	4
+	Benefits of depth in neural networks	2016	Matus Telgarsky	4
+	Towards moderate overparameterization: global convergence guarantees for training shallow neural networks	2019	Samet Oymak Mahdi Soltanolkotabi	4
+	Distribution-specific hardness of learning neural networks	2018	Ohad Shamir	4
+ PDF Chat	A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics	2020	E Weinan Chao Ma Lei Wu	4
+	Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?	2018	Samet Oymak Mahdi Soltanolkotabi	4
+	Diverse Neural Network Learns True Target Functions	2016	Bo Xie Yingyu Liang Le Song	4
+ PDF Chat	Wide neural networks of any depth evolve as linear models under gradient descent <sup>*</sup>	2020	Jaehoon Lee Lechao Xiao Samuel S. Schoenholz Yasaman Bahri Roman Novak Jascha Sohl‐Dickstein Jeffrey Pennington	4
+	Backward Feature Correction: How Deep Learning Performs Deep Learning	2020	Zeyuan Allen-Zhu Yuanzhi Li	3
+	On the number of response regions of deep feed forward networks with piece-wise linear activations	2013	Razvan Pascanu Guido Montúfar Yoshua Bengio	3
+	Representation Benefits of Deep Feedforward Networks	2015	Matus Telgarsky	3
+	Depth Separation for Neural Networks	2017	Amit Daniely	3
+	Failures of Gradient-Based Deep Learning	2017	Shai Shalev‐Shwartz Ohad Shamir Shaked Shammah	3
+	Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs	2017	Alon Brutzkus Amir Globerson	3
+	Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks	2018	Mahdi Soltanolkotabi Adel Javanmard Jason D. Lee	3
+	On the Expressive Power of Deep Learning: A Tensor Analysis	2015	Nadav Cohen Or Sharir Amnon Shashua	3
+	An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis	2017	Yuandong Tian	2
+	A complete characterization of statistical query learning with applications to evolvability	2012	Vitaly Feldman	2
+	Bounding and Counting Linear Regions of Deep Neural Networks	2017	Thiago Serra Christian Tjandraatmadja Srikumar Ramalingam	2
+ PDF Chat	Linearized two-layers neural networks in high dimension	2021	Behrooz Ghorbani Mei Song Theodor Misiakiewicz Andrea Montanari	2
+	Decision trees are PAC-learnable from most product distributions: a smoothed analysis	2008	Adam Tauman Kalai Shang‐Hua Teng	2
+	Deep Learning and Hierarchal Generative Models.	2016	Elchanan Mossel	2
+	A Provably Correct Algorithm for Deep Learning that Actually Works	2018	Eran Malach Shai Shalev‐Shwartz	2
+	On the Number of Linear Regions of Deep Neural Networks	2014	Guido Montúfar Razvan Pascanu Kyunghyun Cho Yoshua Bengio	2
+	Poly-time universality and limitations of deep learning	2020	Emmanuel Abbé Colin Sandon	2
+	Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity	2020	Pritish Kamath Omar Montasser Nathan Srebro	2
+ PDF Chat	Deep vs. shallow networks: An approximation theory perspective	2016	H. N. Mhaskar Tomaso Poggio	2
+	In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning	2014	Behnam Neyshabur Ryota Tomioka Nathan Srebro	2
+	When is a Convolutional Filter Easy To Learn?	2017	Simon S. Du Jason D. Lee Yuandong Tian	2
+	Beyond the low-degree algorithm: mixtures of subcubes and their applications	2019	Sitan Chen Ankur Moitra	2
+	ID3 Learns Juntas for Smoothed Product Distributions	2019	Alon Brutzkus Amit Daniely Eran Malach	2
+	On the Expressive Power of Deep Neural Networks	2016	Maithra Raghu Ben Poole Jon Kleinberg Surya Ganguli Jascha Sohl‐Dickstein	2
+	Recovery Guarantees for One-hidden-layer Neural Networks	2017	Kai Zhong Zhao Song Prateek Jain Peter L. Bartlett Inderjit S. Dhillon	2
+	What Can ResNet Learn Efficiently, Going Beyond Kernels?	2019	Zeyuan Allen-Zhu Yuanzhi Li	2
+	SGD Learns the Conjugate Kernel Class of the Network	2017	Amit Daniely	2
+	Provable limitations of deep learning.	2018	Emmanuel Abbé Colin Sandon	2
+	Neural Tangent Kernel: Convergence and Generalization in Neural Networks	2018	Arthur Paul Jacot Franck Gabriel Clément Hongler	2
+	What Can ResNet Learn Efficiently, Going Beyond Kernels?	2019	Zeyuan Allen-Zhu Yuanzhi Li	2
+	Depth Creates No Bad Local Minima	2017	Haihao Lu Kenji Kawaguchi	1
+ PDF Chat	Analysis of a Random Forests Model	2010	Gérard Biau	1
+ PDF Chat	Uniform approximation of functions with random bases	2008	Ali Rahimi Benjamin Recht	1
+	Gradient Descent Learns Linear Dynamical Systems	2016	Moritz Hardt Tengyu Ma Benjamin Recht	1
+	Convexified Convolutional Neural Networks	2016	Yuchen Zhang Percy Liang Martin J. Wainwright	1
+	On the Connection Between Learning Two-Layers Neural Networks and Tensor Decomposition	2018	Marco Mondelli Andrea Montanari	1