paper-with-me

홈 › Papers

Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

2025-06-16 · Michael Crawshaw, Blake Woodworth, Mingrui Liu

Existing analysis of Local (Stochastic) Gradient Descent for heterogeneous objectives requires stepsizes $\eta \leq 1/K$ where $K$ is the communication interval, which ensures monotonic decrease of the objective. In contrast, we analyze Local Gradient Descent for logistic regression with separable, heterogeneous data using any stepsize $\eta > 0$. With $R$ communication rounds and $M$ clients, we show convergence at a rate $\mathcal{O}(1/\eta K R)$ after an initial unstable phase lasting for $\widetilde{\mathcal{O}}(\eta K M)$ rounds. This improves upon the existing $\mathcal{O}(1/R)$ rate for general smooth, convex objectives. Our analysis parallels the single machine analysis of~\cite{wu2024large} in which instability is caused by extremely large stepsizes, but in our setting another source of instability is large local updates with heterogeneous objectives.

📄 PDF Abstract BibTeX arXiv:2506.13974

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…

Similar Papers 제목 키워드 기반

Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency

2024-02-24 · Jingfeng Wu, Peter L. Bartlett, Matus Telgarsky, Bin Yu

We consider gradient descent (GD) with a constant stepsize applied to logistic regression with linearly separable data, where the constant stepsize $\eta$ is so large that the loss initially oscillates. We show that GD e…

General Classification

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

2023-05-19 · NeurIPS 2023 11

Recent research has observed that in machine learning optimization, gradient descent (GD) often operates at the edge of stability (EoS) [Cohen, et al., 2021], where the stepsizes are set to be large, resulting in non-mon…

regression

Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes

2025-04-05 · Ruiqi Zhang, Jingfeng Wu, Licong Lin, Peter L. Bartlett

We study $\textit{gradient descent}$ (GD) for logistic regression on linearly separable data with stepsizes that adapt to the current risk, scaled by a constant hyperparameter $\eta$. We show that after at most $1/\gamma…

Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

2025-01-23 · Michael Crawshaw, Blake Woodworth, Mingrui Liu

We analyze two variants of Local Gradient Descent applied to distributed logistic regression with heterogeneous, separable data and show convergence at the rate $O(1/KR)$ for $K$ local steps and sufficiently large $R$ co…

regression

Adaptive Gradient Descent without Descent

2019-10-21 · ICML 2020 1 · Yura Malitsky, Konstantin Mishchenko

We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature. No need for functional values, no line s…