paper-with-me

홈 › Papers

Adaptive Decentralized Composite Optimization via Three-Operator Splitting

2026-02-19 · Xiaokai Chen, Ilya Kuruzov, Gesualdo Scutari arxiv

The paper studies decentralized optimization over networks, where agents minimize a sum of {\it locally} smooth (strongly) convex losses and plus a nonsmooth convex extended value term. We propose decentralized methods wherein agents {\it adaptively} adjust their stepsize via local backtracking procedures coupled with lightweight min-consensus protocols. Our design stems from a three-operator splitting factorization applied to an equivalent reformulation of the problem. The reformulation is endowed with a new BCV preconditioning metric (Bertsekas-O'Connor-Vandenberghe), which enables efficient decentralized implementation and local stepsize adjustments. We establish robust convergence guarantees. Under mere convexity, the proposed methods converge with a sublinear rate. Under strong convexity of the sum-function, and assuming the nonsmooth component is partly smooth, we further prove linear convergence. Numerical experiments corroborate the theory and highlight the effectiveness of the proposed adaptive stepsize strategy.

📄 PDF Abstract BibTeX arXiv:2602.17545

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decentralized Inexact Proximal Gradient Method With Network-Independent Stepsizes for Convex Composite Optimization

2023-02-07 · Luyao Guo, Xinli Shi, Jinde Cao, ZiHao Wang

This paper proposes a novel CTA (Combine-Then-Adapt)-based decentralized algorithm for solving convex composite optimization problems over undirected and connected networks. The local loss function in these problems cont…

PMGT-VR: A decentralized proximal-gradient algorithmic framework with variance reduction

2020-12-30 · Haishan Ye, Wei Xiong, Tong Zhang

This paper considers the decentralized composite optimization problem. We propose a novel decentralized variance-reduction proximal-gradient algorithmic framework, called PMGT-VR, which is based on a combination of sever…

Operator Calculus for Population-Based Optimization: A Mean-Field Convergence Theory

2026-06-12 · Pekka Malo, Lauri Viitasaari, Patrik Nummi, Antti Suominen 외 arxiv

Population-based and distributional optimization methods, from evolution strategies and consensus-based optimization to covariance-matrix adaptation and stochastic gradient methods viewed as distributional dynamics, are …

Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising

2022-08-02 · Junqi Tang, Matthias Ehrhardt, Carola-Bibiane Schönlieb

In this work we propose a stochastic primal-dual three-operator splitting algorithm (TOS-SPDHG) for solving a class of convex three-composite optimization problems. Our proposed scheme is a direct three-operator splittin…

Denoising

FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression

2024-10-16 · Zhenheng Tang, Xueze Kang, Yiming Yin, Xinglin Pan 외

To alleviate hardware scarcity in training large deep neural networks (DNNs), particularly large language models (LLMs), we present FusionLLM, a decentralized training system designed and implemented for training DNNs us…

Scheduling