Communication-efficient Byzantine-robust distributed learning with statistical guarantee

TL;DR

This paper introduces two communication-efficient, Byzantine-robust distributed learning algorithms for convex problems, achieving optimal statistical rates and demonstrating strong robustness and efficiency through theoretical guarantees and empirical results.

Contribution

The paper proposes novel algorithms that combine communication efficiency with Byzantine robustness, supported by provable statistical guarantees for convex learning problems.

Findings

Algorithms are robust against Byzantine failures.

Achieve optimal statistical rates for convex problems.

Demonstrated effectiveness through simulations and real data.

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.