Communication-efficient Byzantine-robust distributed learning with statistical guarantee
This work addresses communication and robustness issues in distributed learning for applications with limited or adversarial nodes, representing an incremental improvement with specific gains.
The paper tackled the dual challenges of communication efficiency and robustness to adversarial nodes in distributed learning by developing two algorithms based on surrogate likelihood and robust aggregation operations, achieving optimal statistical rates for convex problems and demonstrating performance through experiments.
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.