The Benefits of Implicit Regularization from SGD in Least Squares
Problems

The Benefits of Implicit Regularization from SGD in Least Squares Problems

10 August 2021

Vladimir Braverman

Quanquan Gu

Dean Phillips Foster

Papers citing "The Benefits of Implicit Regularization from SGD in Least Squares Problems"

8 / 8 papers shown

Title
$On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression$ On the Optimal Weighted $\ell_2$ Regularization in Overparameterized Linear Regression Denny Wu Ji Xu 67 122 0 10 Jun 2020
Bad Global Minima Exist and SGD Can Reach Them Shengchao Liu Dimitris Papailiopoulos D. Achlioptas 54 80 0 06 Jun 2019
Implicit Regularization in Deep Matrix Factorization Sanjeev Arora Nadav Cohen Wei Hu Yuping Luo AI4CE 78 503 0 31 May 2019
Surprises in High-Dimensional Ridgeless Least Squares Interpolation Trevor Hastie Andrea Montanari Saharon Rosset Robert Tibshirani 188 743 0 19 Mar 2019
Understanding deep learning requires rethinking generalization Chiyuan Zhang Samy Bengio Moritz Hardt Benjamin Recht Oriol Vinyals HAI 339 4,626 0 10 Nov 2016
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 424 2,937 0 15 Sep 2016
In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning Behnam Neyshabur Ryota Tomioka Nathan Srebro AI4CE 90 657 0 20 Dec 2014
Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n) Francis R. Bach Eric Moulines 89 405 0 10 Jun 2013