8 citations · 18 across the 9 of their papers we have counts for
4 papers · 1 filter
A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
Puning Zhao, Fei Yu, Zhiguo Wan
Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive the…
Minimax Optimal Q Learning with Nearest Neighbors
Puning Zhao, Lifeng Lai
Analyzing the Markov decision process (MDP) with continuous state spaces is generally challenging. A recent interesting work \cite{shah2018q} solves MDP with bounded continuous sta…
High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers
Wenyu Liu, Tianqiang Huang, Pengfei Zhang +3
Adversarial attacks pose a major challenge to distributed learning systems, prompting the development of numerous robust learning methods. However, most existing approaches suffer…
Optimal Stochastic Nonconvex Optimization with Bandit Feedback
Puning Zhao, Lifeng Lai
In this paper, we analyze the continuous armed bandit problems for nonconvex cost functions under certain smoothness and sublevel set assumptions. We first derive an upper bound on…