Communication-efficient Byzantine-robust distributed learning with statistical guarantee

Abstract

Communication efficiency and robustness are two major issues in modern distributed learning framework. This is due to the practical situations where some computing nodes may have limited communication power or may behave adversarial behaviors. To address the two issues simultaneously, this paper develops two communication-efficient and robust distributed learning algorithms for convex problems. Our motivation is based on surrogate likelihood framework and the median and trimmed mean operations. Particularly, the proposed algorithms are provably robust against Byzantine failures, and also achieve optimal statistical rates for strong convex losses and convex (non-smooth) penalties. For typical statistical models such as generalized linear models, our results show that statistical errors dominate optimization errors in finite iterations. Simulated and real data experiments are conducted to demonstrate the numerical performance of our algorithms.

arXiv comment34 pages

References in corpus (7)

• Federated Learning: Strategies for Improving Communication Efficiency
• Communication Efficient Distributed Optimization using an Approximate Newton-type Method
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• Geometric median and robust estimation in Banach spaces
• Generalized Byzantine-tolerant SGD
• Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
• Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch-Prox