Can I read Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update on EtoBox?

Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update by Wang, Jing; Zhang, Yu-Jie; Zhao, Peng; Zhou, Zhi-Hua is a scholarly article available to read on EtoBox.

What is Heavy-Tailed Linear Bandits: Huber Regression with One-Pass Update about?

We study the stochastic linear bandits with heavy-tailed noise. Two principled strategies for handling heavy-tailed noise, truncation and median-of-means, have been introduced to heavy-tailed bandits. Nonetheless, these methods rely on specific noise assumptions or bandit structures, limiting their applicability to general settings. The recent work [Huang et al.2024] develops a soft truncation method via the adaptive Huber regression to address these limitations. However, their method suffers undesired computational cost: it requires storing all historical data and performing a full pass over these data at each round. In this paper, we propose a \emph{one-pass} algorithm based on the online mirror descent framework. Our method updates using only current data at each round, reducing the per-round computational cost from $\widetilde{\mathcal{O}}(t \log T)$ to $\widetilde{\mathcal{O}}(1)$ with respect to current round $t$ and the time horizon $T$, and achieves a near-optimal and variance-aware regret of order $\widetilde{\mathcal{O}}\big(d T^{\frac{1-\epsilon}{2(1+\epsilon)}} \sqrt{\sum_{t=1}^T \nu_t^2} + d T^{\frac{1-\epsilon}{2(1+\epsilon)}}\big)$ where $d$ is the dimension and $\nu

Author

Wang, Jing; Zhang, Yu-Jie; Zhao, Peng; Zhou, Zhi-Hua

Published

2025

Language

EN