Byzantine-Robust Decentralized Stochastic Optimization over Static and Time-Varying Networks

Abstract

In this paper, we consider the Byzantine-robust stochastic optimization problem defined over decentralized static and time-varying networks, where the agents collaboratively minimize the summation of expectations of stochastic local cost functions, but some of the agents are unreliable due to data corruptions, equipment failures or cyber-attacks. The unreliable agents, which are called as Byzantine agents thereafter, can send faulty values to their neighbors and bias the optimization process. Our key idea to handle the Byzantine attacks is to formulate a total variation (TV) norm-penalized approximation of the Byzantine-free problem, where the penalty term forces the local models of regular agents to be close, but also allows the existence of outliers from the Byzantine agents. A stochastic subgradient method is applied to solve the penalized problem. We prove that the proposed method reaches a neighborhood of the Byzantine-free optimal solution, and the size of neighborhood is determined by the number of Byzantine agents and the network topology. Numerical experiments corroborate the theoretical analysis, as well as demonstrate the robustness of the proposed method to Byzantine attacks and its superior performance comparing to existing methods.

References in corpus (9)

• Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks
• Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
• D${}^2$: Decentralized Training over Decentralized Data
• Generalized Byzantine-tolerant SGD
• DSA: Decentralized Double Stochastic Averaging Gradient Algorithm
• Resilient Distributed Parameter Estimation with Heterogeneous Data
• Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data
• Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite Sums
• Gradient tracking and variance reduction for decentralized optimization and machine learning