Anti-Distillation: Improving reproducibility of deep networks

Gil I. Shamir, Lorenzo Coviello

Type: Preprint

Publication Date: 2020-01-01

Citations: 4

DOI: https://doi.org/10.48550/arxiv.2010.09923

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Anti-Distillation: Improving Reproducibility of Deep Networks	2021	Gil I. Shamir Lorenzo Coviello
+	Hydra: Preserving Ensemble Diversity for Model Distillation	2020	Linh Tran Bastiaan S. Veeling Kevin A. Roth Jakub Świątkowski Joshua V. Dillon Jasper Snoek Stephan Mandt Tim Salimans Sebastian Nowozin Rodolphe Jenatton
+	Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning	2020	Zeyuan Allen-Zhu Yuanzhi Li
+	Functional Ensemble Distillation	2022	Coby Penso Idan Achituve Ethan Fetaya
+	Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study	2023	Lirui Zhao Yuxin Zhang Mingbao Lin Fei Chao Rongrong Ji
+	On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective	2020	SeongUk Park KiYoon Yoo Nojun Kwak
+	Churn Reduction via Distillation	2021	Heinrich Jiang Harikrishna Narasimhan Dara Bahri Andrew Cotter Afshin Rostamizadeh
+ PDF Chat	Churn Reduction via Distillation	2021	Heinrich Jiang Harikrishna Narasimhan Dara Bahri Andrew Cotter Afshin Rostamizadeh
+	Towards Mitigating Architecture Overfitting in Dataset Distillation	2023	Xuyang Zhong Chen Liu
+	Ensemble Distribution Distillation	2020	Andrey Malinin Bruno Mlodozeniec Mark Gales
+	Ensemble Distribution Distillation	2019	Andrey Malinin Bruno Mlodozeniec Mark Gales
+ PDF Chat	A General Framework for Ensemble Distribution Distillation	2020	Jakob Lindqvist Amanda Olmin Fredrik Lindsten Lennart Svensson
+	On the Reproducibility of Neural Network Predictions	2021	Srinadh Bhojanapalli Michael J. Wilber Andreas Veit Ankit Singh Rawat Seung‐Yeon Kim Aditya Krishna Menon Sanjiv Kumar
+	DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation	2021	Alexandre Ramé Matthieu Cord
+	Using Early Readouts to Mediate Featural Bias in Distillation	2023	Rishabh Tiwari Durga Sivasubramanian Anmol Mekala Ganesh Ramakrishnan Pradeep Shenoy
+ PDF Chat	Using Early Readouts to Mediate Featural Bias in Distillation	2024	Rishabh Tiwari Durga Sivasubramanian Anmol Mekala Ganesh Ramakrishnan Pradeep Shenoy
+	Simple Regularisation for Uncertainty-Aware Knowledge Distillation	2022	Martin Ferianc Miguel Tréfaut Rodrigues
+	Deep Ensembles Work, But Are They Necessary?	2022	Taiga Abe E. Kelly Buchanan Geoff Pleiss Richard S. Zemel John P. Cunningham
+	EnsembleNet: End-to-End Optimization of Multi-headed Models	2019	Hanhan Li Joe Yue-Hei Ng Apostol Natsev
+	Self-Distribution Distillation: Efficient Uncertainty Estimation	2022	Yassir Fathullah Mark Gales

Works That Cite This (0)

Action	Title	Year	Authors

Works Cited by This (0)

Action	Title	Year	Authors