paper-with-me

Papers

Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication

2018-05-25 · ICML 2018 7 · Zebang Shen, Aryan Mokhtari, Tengfei Zhou, Peilin Zhao, Hui Qian

Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number. Besides, the dense communication is necessary to ensure the convergence even if the dataset is sparse. In this paper, we generalize the decentralized optimization problem to a monotone operator root finding problem, and propose a stochastic algorithm named DSBA that (i) converges geometrically with a rate linearly depending on the problem condition number, and (ii) can be implemented using sparse communication only. Additionally, DSBA handles learning problems like AUC-maximization which cannot be tackled efficiently in the decentralized setting. Experiments on convex minimization and AUC-maximization validate the efficiency of our method.

📄 PDF Abstract BibTeX arXiv:1805.09969

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

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 l…

image-classificationImage Classification

MATCHA: Speeding Up Decentralized SGD via Matching Decomposition Sampling

2019-05-23 · Jianyu Wang, Anit Kumar Sahu, Zhouyi Yang, Gauri Joshi 외

This paper studies the problem of error-runtime trade-off, typically encountered in decentralized training based on stochastic gradient descent (SGD) using a given network. While a denser (sparser) network topology resul…

Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks

2024-01-24 · Daniel Pérez Herrera, Zheng Chen, Erik G. Larsson

Consensus-based decentralized stochastic gradient descent (D-SGD) is a widely adopted algorithm for decentralized training of machine learning models across networked agents. A crucial part of D-SGD is the consensus-base…

Scheduling

On the Communication Complexity of Decentralized Bilevel Optimization

2023-11-19 · Yihan Zhang, My T. Thai, Jie Wu, Hongchang Gao

Stochastic bilevel optimization finds widespread applications in machine learning, including meta-learning, hyperparameter optimization, and neural architecture search. To extend stochastic bilevel optimization to distri…

Bilevel OptimizationHyperparameter OptimizationMeta-LearningNeural Architecture Search

Fast Training Method for Stochastic Compositional Optimization Problems

2021-12-01 · NeurIPS 2021 12 · Hongchang Gao, Heng Huang

The stochastic compositional optimization problem covers a wide range of machine learning models, such as sparse additive models and model-agnostic meta-learning. Thus, it is necessary to develop efficient methods for i…

Additive modelsMeta-Learning