Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

In this paper, we develop distributed optimization algorithms that are provably robust against
Byzantine failures—arbitrary and potentially adversarial behavior, in distributed computing …

Multi-armed bandit problems are the most basic examples of sequential decision problems
with an exploration-exploitation trade-off. This is the balance between staying with the option …

Emerging Distributed AI systems are revolutionizing big data computing and data
processing capabilities with growing economic and societal impact. However, recent studies …

While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning,
adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across …

We survey some of the recent advances in mean estimation and regression function
estimation. In particular, we describe sub-Gaussian mean estimators for possibly heavy …

We introduce a new model of stochastic bandits with adversarial corruptions which aims to
capture settings where most of the input follows a stochastic pattern but some fraction of it …

Federated learning (FL) coordinates with numerous heterogeneous devices to
collaboratively train a shared model while preserving user privacy. Despite its multiple …

We study the stochastic multi-armed bandits problem in the presence of adversarial
corruption. We present a new algorithm for this problem whose regret is nearly optimal …

In many real-world applications, collected data are contaminated by noise with heavy-tailed
distribution and might contain outliers of large magnitude. In this situation, it is necessary to …