paper-with-me

홈 › Papers

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 $R$ communication rounds. In contrast, all existing convergence guarantees for Local GD applied to any problem are at least $\Omega(1/R)$, meaning they fail to show the benefit of local updates. The key to our improved guarantee is showing progress on the logistic regression objective when using a large stepsize $\eta \gg 1/K$, whereas prior analysis depends on $\eta \leq 1/K$.

📄 PDF Abstract BibTeX arXiv:2501.13790

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

HADFL: Heterogeneity-aware Decentralized Federated Learning Framework

2021-11-16 · Jing Cao, Zirui Lian, Weihong Liu, Zongwei Zhu 외

Federated learning (FL) supports training models on geographically distributed devices. However, traditional FL systems adopt a centralized synchronous strategy, putting high communication pressure and model generalizati…

Federated Learning

The Role of Local Steps in Local SGD

2022-03-14 · Tiancheng Qin, S. Rasoul Etesami, César A. Uribe

We consider the distributed stochastic optimization problem where $n$ agents want to minimize a global function given by the sum of agents' local functions, and focus on the heterogeneous setting when agents' local funct…

Stochastic Optimization

Unifying Local Communications and Local Updates for LLM Pretraining

2026-06-09 · Pietro Cagnasso, Eugene Belilovsky, Edouard Oyallon arxiv

Communication-efficient pre-training of LLMs is increasingly important as training draws on compute distributed across clusters, data centers, and lower-bandwidth links. Many practical methods reduce communication freque…

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…

Distributed and Stochastic Optimization Methods with Gradient Compression and Local Steps

2021-12-20 · Eduard Gorbunov

In this thesis, we propose new theoretical frameworks for the analysis of stochastic and distributed methods with error compensation and local updates. Using these frameworks, we develop more than 20 new optimization met…

Stochastic Optimization