Benign Overfitting of Constant-Stepsize SGD for Linear Regression

Benign Overfitting of Constant-Stepsize SGD for Linear Regression

23 March 2021

Vladimir Braverman

Quanquan Gu

Papers citing "Benign Overfitting of Constant-Stepsize SGD for Linear Regression"

10 / 10 papers shown

Title
Better Rates for Random Task Orderings in Continual Linear Models Itay Evron Ran Levinstein Matan Schliserman Uri Sherman Tomer Koren Daniel Soudry Nathan Srebro CLL 35 0 0 06 Apr 2025
How Does Critical Batch Size Scale in Pre-training? Hanlin Zhang Depen Morwani Nikhil Vyas Jingfeng Wu Difan Zou Udaya Ghai Dean Phillips Foster Sham Kakade 75 8 0 29 Oct 2024
Scaling Laws in Linear Regression: Compute, Parameters, and Data Licong Lin Jingfeng Wu Sham Kakade Peter L. Bartlett Jason D. Lee LRM 41 15 0 12 Jun 2024
Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression Bhavya Agrawalla Krishnakumar Balasubramanian Promit Ghosal 25 2 0 20 Feb 2023
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks Luca Arnaboldi Ludovic Stephan Florent Krzakala Bruno Loureiro MLT 30 31 0 12 Feb 2023
Non-reversible Parallel Tempering for Deep Posterior Approximation Wei Deng Qian Zhang Qi Feng F. Liang Guang Lin 20 4 0 20 Nov 2022
Provable Generalization of Overparameterized Meta-learning Trained with SGD Yu Huang Yingbin Liang Longbo Huang MLT 26 8 0 18 Jun 2022
Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions Maksim Velikanov Dmitry Yarotsky 9 6 0 02 Feb 2022
Benign Overfitting in Adversarially Robust Linear Classification Jinghui Chen Yuan Cao Quanquan Gu AAML SILM 31 10 0 31 Dec 2021
A Theoretical Analysis of Fine-tuning with Linear Teachers Gal Shachaf Alon Brutzkus Amir Globerson 31 17 0 04 Jul 2021