Compressed Distributed Gradient Descent: Communication-Efficient Consensus over Networks
arXiv:1812.04048
Abstract
Network consensus optimization has received increasing attention in recent years and has found important applications in many scientific and engineering fields. To solve network consensus optimization problems, one of the most well-known approaches is the distributed gradient descent method (DGD). However, in networks with slow communication rates, DGD's performance is unsatisfactory for solving high-dimensional network consensus problems due to the communication bottleneck. This motivates us to design a communication-efficient DGD-type algorithm based on compressed information exchanges. Our contributions in this paper are three-fold: i) We develop a communication-efficient algorithm called amplified-differential compression DGD (ADC-DGD) and show that it converges under {\em any} unbiased compression operator; ii) We rigorously prove the convergence performances of ADC-DGD and show that they match with those of DGD without compression; iii) We reveal an interesting phase transition phenomenon in the convergence speed of ADC-DGD. Collectively, our findings advance the state-of-the-art of network consensus optimization theory.
11 pages, 11 figures, IEEE INFOCOM 2019
References in corpus (8)
- QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
- TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
- Gradient Sparsification for Communication-Efficient Distributed Optimization
- Efficient Distributed Learning with Sparsity
- Communication-Efficient Distributed Statistical Inference
- On Nonconvex Decentralized Gradient Descent
- Balancing Communication and Computation in Distributed Optimization
- Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning