paper-with-me

Papers

Optimal Complexity in Decentralized Training

2020-06-15 · Yucheng Lu, Christopher De Sa

Decentralization is a promising method of scaling up parallel machine learning systems. In this paper, we provide a tight lower bound on the iteration complexity for such methods in a stochastic non-convex setting. Our lower bound reveals a theoretical gap in known convergence rates of many existing decentralized training algorithms, such as D-PSGD. We prove by construction this lower bound is tight and achievable. Motivated by our insights, we further propose DeTAG, a practical gossip-style decentralized algorithm that achieves the lower bound with only a logarithm gap. Empirically, we compare DeTAG with other decentralized algorithms on image classification tasks, and we show DeTAG enjoys faster convergence compared to baselines, especially on unshuffled data and in sparse networks.

📄 PDF Abstract BibTeX arXiv:2006.08085

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Decentralized Accelerated Proximal Gradient Descent

2020-12-01 · NeurIPS 2020 12 · Haishan Ye, Ziang Zhou, Luo Luo, Tong Zhang

Decentralized optimization has wide applications in machine learning, signal processing, and control. In this paper, we study the decentralized composite optimization problem with a non-smooth regularization term…

BIG-bench Machine Learning

Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks

2022-11-01 · Xinmeng Huang, Kun Yuan

Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especial…

Federated LearningStochastic Optimization

Faster Adaptive Decentralized Learning Algorithms

2024-08-19 · Feihu Huang, Jianyu Zhao

Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show …

Stochastic Optimization

Near-Optimal Decentralized Stochastic Nonconvex Optimization with Heavy-Tailed Noise

2026-01-16 · Menglian Wang, Zhuanghua Liu, Luo Luo arxiv

This paper studies decentralized stochastic nonconvex optimization problem over row-stochastic networks. We consider the heavy-tailed gradient noise which is empirically observed in many popular real-world applications. …

Decentralized and Equitable Optimal Transport

2024-03-07 · Ivan Lau, Shiqian Ma, César A. Uribe

This paper considers the decentralized (discrete) optimal transport (D-OT) problem. In this setting, a network of agents seeks to design a transportation plan jointly, where the cost function is the sum of privately held…