paper-with-me

홈 › Papers

A Simplified Analysis of SGD for Linear Regression with Weight Averaging

2025-06-18 · Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu, Jingfeng Wu, Cengiz Pehlevan, Sham Kakade

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides sharp rates for SGD optimization in linear regression using constant learning rate, both with and without tail iterate averaging, based on a bias-variance decomposition of the risk. In our work, we provide a simplified analysis recovering the same bias and variance bounds provided in~\citep{zou2021benign} based on simple linear algebra tools, bypassing the requirement to manipulate operators on positive semi-definite (PSD) matrices. We believe our work makes the analysis of SGD on linear regression very accessible and will be helpful in further analyzing mini-batching and learning rate scheduling, leading to improvements in the training of realistic models.

📄 PDF Abstract BibTeX arXiv:2506.15535

Code (0)

등록된 구현이 없습니다.

Tasks

regressionScheduling

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Distributed linear regression by averaging

2018-09-30 · Edgar Dobriban, Yue Sheng

Distributed statistical learning problems arise commonly when dealing with large datasets. In this setup, datasets are partitioned over machines, which compute locally, and communicate short messages. Communication is of…

regression

Nested Model Averaging on Solution Path for High-dimensional Linear Regression

2020-05-16 · Yang Feng, Qing-Feng Liu

We study the nested model averaging method on the solution path for a high-dimensional linear regression problem. In particular, we propose to combine model averaging with regularized estimators (e.g., lasso and SLOPE) o…

regressionVocal Bursts Intensity Prediction

Iterate averaging as regularization for stochastic gradient descent

2018-02-22 · Gergely Neu, Lorenzo Rosasco

We propose and analyze a variant of the classic Polyak-Ruppert averaging scheme, broadly used in stochastic gradient methods. Rather than a uniform average of the iterates, we consider a weighted average, with weights de…

regression

Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging

2026-02-03 · Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan 외 arxiv

Large language models are increasingly trained in continual or open-ended settings, where the total training horizon is not known in advance. Despite this, most existing pretraining recipes are not anytime: they rely on …

Weighted-Average Least Squares for Negative Binomial Regression

2024-04-17 · Kevin Huynh

Model averaging methods have become an increasingly popular tool for improving predictions and dealing with model uncertainty, especially in Bayesian settings. Recently, frequentist model averaging methods such as inform…

regression