Can we avoid Double Descent in Deep Neural Networks?

26 February 2023

Papers citing "Can we avoid Double Descent in Deep Neural Networks?"

18 / 18 papers shown

Title
Multiple Descent in the Multiple Random Feature Model Xuran Meng Jianfeng Yao Yuan Cao 54 7 0 21 Aug 2022
To update or not to update? Neurons at equilibrium in deep models Andrea Bragagnolo Enzo Tartaglione Marco Grangetto 48 10 0 19 Jul 2022
Sparse Double Descent: Where Network Pruning Aggravates Overfitting Zhengqi He Zeke Xie Quanzhi Zhu Zengchang Qin 109 27 0 17 Jun 2022
Regularization-wise double descent: Why it occurs and how to eliminate it Fatih Yilmaz Reinhard Heckel 50 11 0 03 Jun 2022
The rise of the lottery heroes: why zero-shot pruning is hard Enzo Tartaglione 43 6 0 24 Feb 2022
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin B. Guo ViT 324 21,175 0 25 Mar 2021
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks Xiangyu Chang Yingcong Li Samet Oymak Christos Thrampoulidis 52 50 0 16 Dec 2020
Optimal Regularization Can Mitigate Double Descent Preetum Nakkiran Prayaag Venkat Sham Kakade Tengyu Ma 67 130 0 04 Mar 2020
Multi-task self-supervised learning for Robust Speech Recognition Mirco Ravanelli Jianyuan Zhong Santiago Pascual P. Swietojanski João Monteiro J. Trmal Yoshua Bengio SSL 219 289 0 25 Jan 2020
Deep Double Descent: Where Bigger Models and More Data Hurt Preetum Nakkiran Gal Kaplun Yamini Bansal Tristan Yang Boaz Barak Ilya Sutskever 105 925 0 04 Dec 2019
Harmless interpolation of noisy data in regression Vidya Muthukumar Kailas Vodrahalli Vignesh Subramanian A. Sahai 47 204 0 21 Mar 2019
The State of Sparsity in Deep Neural Networks Trevor Gale Erich Elsen Sara Hooker 103 755 0 25 Feb 2019
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 174 1,628 0 28 Dec 2018
A jamming transition from under- to over-parametrization affects loss landscape and generalization S. Spigler Mario Geiger Stéphane dÁscoli Levent Sagun Giulio Biroli Matthieu Wyart 51 152 0 22 Oct 2018
The jamming transition as a paradigm to understand the loss landscape of deep neural networks Mario Geiger S. Spigler Stéphane dÁscoli Levent Sagun Marco Baity-Jesi Giulio Biroli Matthieu Wyart 46 141 0 25 Sep 2018
Dimensionality-Driven Learning with Noisy Labels Xingjun Ma Yisen Wang Michael E. Houle Shuo Zhou S. Erfani Shutao Xia S. Wijewickrema James Bailey NoLa 58 429 0 07 Jun 2018
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks Jonathan Frankle Michael Carbin 170 3,433 0 09 Mar 2018
Learning both Weights and Connections for Efficient Neural Networks Song Han Jeff Pool J. Tran W. Dally CVBM 247 6,628 0 08 Jun 2015