← Search

Ambrus Tamás

2 accepted papers

2025

Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits

AISTATS 2025poster

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit algorithms, as it achieves near-optimal regret rates under vario…

Cited by 0SourceScholar
2024

Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions

AISTATS 2024poster

Estimating the expected value is one of the key problems of statistics, and it serves as a backbone for countless methods in machine learning. In this paper we propose a new algorithm to build non-asymptotically exact confidence intervals for the mean of a symmetric distribution based on an independ…

Cited by 2SourcePDFScholar