A mirror descent variant whose potential adapts to the heaviness of the loss tail, achieving instance-optimal regret without prior tail knowledge.
Preprint arXiv Bandits and online learning
Adaptive Mirror Descent for Heavy-Tailed Bandits
arXiv:2604.09812
Cite this paper
Adaptive Mirror Descent for Heavy-Tailed Bandits
@inproceedings{aydn2026mirror,
title = {Adaptive Mirror Descent for Heavy-Tailed Bandits},
author = {Leila Aydın and Maya Singh and Renat Ostrovsky},
booktitle = {arXiv},
year = {2026},
url = {https://arxiv.org/abs/2604.09812}
}