paper-with-me

Papers

Local SGD in Overparameterized Linear Regression

2022-10-20 · Mike Nguyen, Charly Kirst, Nicole Mücke

We consider distributed learning using constant stepsize SGD (DSGD) over several devices, each sending a final model update to a central server. In a final step, the local estimates are aggregated. We prove in the setting of overparameterized linear regression general upper bounds with matching lower bounds and derive learning rates for specific data generating distributions. We show that the excess risk is of order of the variance provided the number of local nodes grows not too large with the global sample size. We further compare the sample complexity of DSGD with the sample complexity of distributed ridge regression (DRR) and show that the excess SGD-risk is smaller than the excess RR-risk, where both sample complexities are of the same order.

📄 PDF Abstract BibTeX arXiv:2210.11562

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

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…
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…

Similar Papers 제목 키워드 기반

Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression

2022-02-12 · NeurIPS 2023 11

One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear reg…

Generalization Boundsregression

Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference

2022-02-02 · Jasper Tan, Blake Mason, Hamid Javadi, Richard G. Baraniuk

A surprising phenomenon in modern machine learning is the ability of a highly overparameterized model to generalize well (small error on the test data) even when it is trained to memorize the training data (zero error on…

Inference AttackMembership Inference Attackregression

More Data Can Hurt for Linear Regression: Sample-wise Double Descent

2019-12-16 · Preetum Nakkiran

In this expository note we describe a surprising phenomenon in overparameterized linear regression, where the dimension exceeds the number of samples: there is a regime where the test risk of the estimator found by gradi…

regression

Distributed Gradient Descent with Many Local Steps in Overparameterized Models

2024-12-10 · Heng Zhu, Harsh Vardhan, Arya Mazumdar

In distributed training of machine learning models, gradient descent with local iterative steps is a very popular method, variants of which are commonly known as Local-SGD or the Federated Averaging (FedAvg). In this met…

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression

2021-10-12 · Jingfeng Wu, Difan Zou, Vladimir Braverman, Quanquan Gu 외

Stochastic gradient descent (SGD) has been shown to generalize well in many deep learning applications. In practice, one often runs SGD with a geometrically decaying stepsize, i.e., a constant initial stepsize followed b…

regression