SGD on Neural Networks Learns Functions of Increasing Complexity

SGD on Neural Networks Learns Functions of Increasing Complexity

28 May 2019

Preetum Nakkiran

Dimitris Kalimeris

Benjamin L. Edelman

Papers citing "SGD on Neural Networks Learns Functions of Increasing Complexity"

11 / 61 papers shown

Title
Learning Optimal Representations with the Decodable Information Bottleneck Yann Dubois Douwe Kiela D. Schwab Ramakrishna Vedantam 28 43 0 27 Sep 2020
Interpreting and Disentangling Feature Components of Various Complexity from DNNs Jie Ren Mingjie Li Zexu Liu Quanshi Zhang CoGe 19 18 0 29 Jun 2020
Implicit Regularization in Deep Learning May Not Be Explainable by Norms Noam Razin Nadav Cohen 24 155 0 13 May 2020
Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization S. Chatterjee ODL OOD 11 51 0 25 Feb 2020
Learning Not to Learn in the Presence of Noisy Labels Liu Ziyin Blair Chen Ru Wang Paul Pu Liang Ruslan Salakhutdinov Louis-Philippe Morency Masahito Ueda NoLa 26 18 0 16 Feb 2020
Towards Understanding the Spectral Bias of Deep Learning Yuan Cao Zhiying Fang Yue Wu Ding-Xuan Zhou Quanquan Gu 41 215 0 03 Dec 2019
The Implicit Bias of Depth: How Incremental Learning Drives Generalization Daniel Gissin Shai Shalev-Shwartz Amit Daniely AI4CE 14 78 0 26 Sep 2019
How Does Learning Rate Decay Help Modern Neural Networks? Kaichao You Mingsheng Long Jianmin Wang Michael I. Jordan 30 4 0 05 Aug 2019
What Makes Training Multi-Modal Classification Networks Hard? Weiyao Wang Du Tran Matt Feiszli 34 443 0 29 May 2019
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 310 2,896 0 15 Sep 2016
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 127 577 0 27 Feb 2015