The Benefits of Implicit Regularization from SGD in Least Squares
Problems

v1v2 (latest)

The Benefits of Implicit Regularization from SGD in Least Squares Problems

10 August 2021

Vladimir Braverman

Quanquan Gu

Dean Phillips Foster

ArXiv (abs)PDF HTML

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

9 / 9 papers shown

Title
Improved Scaling Laws in Linear Regression via Data Reuse Licong Lin Jingfeng Wu Peter Bartlett 22 0 0 10 Jun 2025
Learning Curves of Stochastic Gradient Descent in Kernel Regression Haihan Zhang Weicheng Lin Yuanshi Liu Cong Fang 31 0 0 28 May 2025
Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors Runxi Cheng Feng Xiong Yongxian Wei Wanyun Zhu Chun Yuan MoMe 133 1 0 11 Mar 2025
Scaling Laws in Linear Regression: Compute, Parameters, and Data Licong Lin Jingfeng Wu Sham Kakade Peter L. Bartlett Jason D. Lee LRM 145 20 0 12 Jun 2024
Losing momentum in continuous-time stochastic optimisation Kexin Jin J. Latz Chenguang Liu Alessandro Scagliotti 60 2 0 08 Sep 2022
Implicit Regularization with Polynomial Growth in Deep Tensor Factorization Kais Hariz Hachem Kadri Stéphane Ayache Maher Moakher Thierry Artières 72 3 0 18 Jul 2022
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent Zhiyuan Li Tianhao Wang Jason D. Lee Sanjeev Arora 104 29 0 08 Jul 2022
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability Aviv Tamar Daniel Soudry E. Zisselman OOD OffRL 39 7 0 24 Sep 2021
Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models? Dominic Richards Yan Sun Patrick Rebeschini 72 3 0 26 Aug 2021