paper-with-me

Papers

Stabilized Proximal-Point Methods for Federated Optimization

2024-07-09 · Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich

In developing efficient optimization algorithms, it is crucial to account for communication constraints -- a significant challenge in modern Federated Learning. The best-known communication complexity among non-accelerated algorithms is achieved by DANE, a distributed proximal-point algorithm that solves local subproblems at each iteration and that can exploit second-order similarity among individual functions. However, to achieve such communication efficiency, the algorithm requires solving local subproblems sufficiently accurately resulting in slightly sub-optimal local complexity. Inspired by the hybrid-projection proximal-point method, in this work, we propose a novel distributed algorithm S-DANE. Compared to DANE, this method uses an auxiliary sequence of prox-centers while maintaining the same deterministic communication complexity. Moreover, the accuracy condition for solving the subproblem is milder, leading to enhanced local computation efficiency. Furthermore, S-DANE supports partial client participation and arbitrary stochastic local solvers, making it attractive in practice. We further accelerate S-DANE and show that the resulting algorithm achieves the best-known communication complexity among all existing methods for distributed convex optimization while still enjoying good local computation efficiency as S-DANE. Finally, we propose adaptive variants of both methods using line search, obtaining the first provably efficient adaptive algorithms that could exploit local second-order similarity without the prior knowledge of any parameters.

📄 PDF Abstract BibTeX arXiv:2407.07084

Code (1)

mlolab/s-dane 공식 구현 pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning

2023-08-24 · CVPR 2024 1 · Gihun Lee, Minchan Jeong, Sangmook Kim, Jaehoon Oh 외

Federated Learning (FL) aggregates locally trained models from individual clients to construct a global model. While FL enables learning a model with data privacy, it often suffers from significant performance degradatio…

Continual LearningFederated LearningImage ClassificationKnowledge Distillation+2

Faster federated optimization under second-order similarity

2022-09-06 · Ahmed Khaled, Chi Jin

Federated learning (FL) is a subfield of machine learning where multiple clients try to collaboratively learn a model over a network under communication constraints. We consider finite-sum federated optimization under a …

Federated Learning

Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization

2025-06-06 · Yuki Takezawa, Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich

Reducing communication complexity is critical for efficient decentralized optimization. The proximal decentralized optimization (PDO) framework is particularly appealing, as methods within this framework can exploit func…

Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum

2025-04-17 · Yuan Zhou, Xinli Shi, Xuelong Li, Jiachen Zhong 외

Decentralized Federated Learning (DFL) eliminates the reliance on the server-client architecture inherent in traditional federated learning, attracting significant research interest in recent years. Simultaneously, the o…

Federated Learning

Federated Binary Matrix Factorization using Proximal Optimization

2024-07-01 · Sebastian Dalleiger, Jilles Vreeken, Michael Kamp

Identifying informative components in binary data is an essential task in many research areas, including life sciences, social sciences, and recommendation systems. Boolean matrix factorization (BMF) is a family of metho…

Federated LearningRecommendation Systems