DeepAI AI Chat
Log In Sign Up

Linear Convergent Decentralized Optimization with Compression

by   Xiaorui Liu, et al.

Communication compression has been extensively adopted to speed up large-scale distributed optimization. However, most existing decentralized algorithms with compression are unsatisfactory in terms of convergence rate and stability. In this paper, we delineate two key obstacles in the algorithm design – data heterogeneity and compression error. Our attempt to explicitly overcome these obstacles leads to a novel decentralized algorithm named LEAD. This algorithm is the first LinEAr convergent Decentralized algorithm with communication compression. Our theory describes the coupled dynamics of the inaccurate model propagation and optimization process. We also provide the first consensus error bound without assuming bounded gradients. Empirical experiments validate our theoretical analysis and show that the proposed algorithm achieves state-of-the-art computation and communication efficiency.


page 1

page 2

page 3

page 4


DeepSqueeze: Decentralization Meets Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...

Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression

Achieving communication efficiency in decentralized machine learning has...

Distributed Convex Optimization "Over-the-Air" in Dynamic Environments

This paper presents a decentralized algorithm for solving distributed co...

Decentralized Composite Optimization with Compression

Decentralized optimization and communication compression have exhibited ...

DeepSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...

BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression

Communication efficiency has been widely recognized as the bottleneck fo...

Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence

Information compression is essential to reduce communication cost in dis...