Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence

by   Jiaqi Zhang, et al.

Information compression is essential to reduce communication cost in distributed optimization over peer-to-peer networks. This paper proposes a communication-efficient linearly convergent distributed (COLD) algorithm to solve strongly convex optimization problems. By compressing innovation vectors, which are the differences between decision vectors and their estimates, COLD is able to achieve linear convergence for a class of δ-contracted compressors. We explicitly quantify how the compression affects the convergence rate and show that COLD matches the same rate of its uncompressed version. To accommodate a wider class of compressors that includes the binary quantizer, we further design a novel dynamical scaling mechanism and obtain the linearly convergent Dyna-COLD. Importantly, our results strictly improve existing results for the quantized consensus problem. Numerical experiments demonstrate the advantages of both algorithms under different compressors.


page 2

page 3

page 4

page 6

page 7

page 8

page 9

page 10


Compressed Gradient Tracking Methods for Decentralized Optimization with Linear Convergence

Communication compression techniques are of growing interests for solvin...

On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks

We study the decentralized consensus and stochastic optimization problem...

Linear Convergent Decentralized Optimization with Compression

Communication compression has been extensively adopted to speed up large...

Distributed Adaptive Newton Methods with Globally Superlinear Convergence

This paper considers the distributed optimization problem over a network...

Compressed Distributed Gradient Descent: Communication-Efficient Consensus over Networks

Network consensus optimization has received increasing attention in rece...

Finite-Bit Quantization For Distributed Algorithms With Linear Convergence

This paper studies distributed algorithms for (strongly convex) composit...

Stochastic Gradient Langevin Dynamics on a Distributed Network

Langevin MCMC gradient optimization is a class of increasingly popular m...