Work

Nested Distributed Gradient Methods with Adaptive Quantized Communication

Year: 2019

Type: conference-paper

Abstract: In this paper, we consider minimizing a sum of local convex objective functions in a distributed setting, where communication can be costly. We propose and analyze a class of nested distributed gradient methods with adaptive quantized communication (NEAR-DGD+Q). We show the effect of performing multiple quantized communication steps on the rate of convergence and on the size of the neighborhood of convergence, and prove R-Linear convergence to the exact solution with increasing number of consensus steps and adaptive quantization. We test the performance of the method, as well as some practical variants, on quadratic functions, and show the effects of multiple quantized communication steps in terms of iterations/gradient evaluations, communication and cost.

Source: IEEE Conference on Decision and Control (CDC)

DOI: 10.1109/cdc40024.2019.9029541

Authors: Albert S. Berahas, Charikleia Iakovidou, Ermin Wei

Institutions: Lehigh University, Northwestern University

Language: English

Topic: Distributed Control Multi-Agent Systems

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

Funder: Defense Advanced Research Projects Agency

Award: G7236905731