English
Related papers

Related papers: Tsallis-INF: An Optimal Algorithm for Stochastic a…

200 papers

Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the…

Machine Learning · Statistics 2019-12-09 Cindy Trinh , Emilie Kaufmann , Claire Vernade , Richard Combes

The combinatorial multi-armed bandit (CMAB) is a cornerstone of sequential decision-making framework, dominated by two algorithmic families: UCB-based and adversarial methods such as follow the regularized leader (FTRL) and online mirror…

Machine Learning · Computer Science 2025-12-30 Zichun Ye , Runqi Wang , Xutong Liu , Shuai Li

We investigate a nonstochastic bandit setting in which the loss of an action is not immediately charged to the player, but rather spread over the subsequent rounds in an adversarial way. The instantaneous loss observed by the player at the…

Machine Learning · Computer Science 2022-09-27 Nicolò Cesa-Bianchi , Tommaso Cesari , Roberto Colomboni , Claudio Gentile , Yishay Mansour

We present an algorithm that achieves almost optimal pseudo-regret bounds against adversarial and stochastic bandits. Against adversarial bandits the pseudo-regret is $O(K\sqrt{n \log n})$ and against stochastic bandits the pseudo-regret is…

Machine Learning · Computer Science 2016-05-30 Peter Auer , Chao-Kai Chiang

We derive an alternative proof for the regret of Thompson sampling (\ts) in the stochastic linear bandit setting. While we obtain a regret bound of order $\widetilde{O}(d^{3/2}\sqrt{T})$ as in previous results, the proof sheds new light on…

Machine Learning · Statistics 2019-11-06 Marc Abeille , Alessandro Lazaric

We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform…

Machine Learning · Computer Science 2024-05-28 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Federico Fusco

Motivated by the pressing need for efficient optimization in online recommender systems, we revisit the cascading bandit model proposed by Kveton et al. (2015). While Thompson sampling (TS) algorithms have been shown to be empirically…

Machine Learning · Computer Science 2021-05-18 Zixin Zhong , Wang Chi Cheung , Vincent Y. F. Tan

We address multi-armed bandits (MAB) where the objective is to maximize the cumulative reward under a probabilistic linear constraint. For a few real-world instances of this problem, constrained extensions of the well-known Thompson…

Machine Learning · Computer Science 2020-05-14 Vidit Saxena , Joseph E. Gonzalez , Joakim Jaldén

I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical results, the new algorithm is simple, efficient and…

Machine Learning · Computer Science 2016-02-25 Tor Lattimore

Motivated by economic applications such as recommender systems, we study the behavior of stochastic bandits algorithms under \emph{strategic behavior} conducted by rational actors, i.e., the arms. Each arm is a \emph{self-interested}…

Machine Learning · Computer Science 2020-11-16 Zhe Feng , David C. Parkes , Haifeng Xu

We develop a novel and generic algorithm for the adversarial multi-armed bandit problem (or more generally the combinatorial semi-bandit problem). When instantiated differently, our algorithm achieves various new data-dependent regret…

Machine Learning · Computer Science 2018-06-08 Chen-Yu Wei , Haipeng Luo

We present a modified tuning of the algorithm of Zimmert and Seldin [2020] for adversarial multiarmed bandits with delayed feedback, which in addition to the minimax optimal adversarial regret guarantee shown by Zimmert and Seldin…

Machine Learning · Computer Science 2022-07-01 Saeed Masoudian , Julian Zimmert , Yevgeny Seldin

In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle. We derive the regret bounds corresponding to the convergence…

Machine Learning · Computer Science 2024-02-13 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Andrey Pudovikov

We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specifically, SAO combines the square-root worst-case regret of Exp3…

Machine Learning · Computer Science 2012-02-22 Sebastien Bubeck , Aleksandrs Slivkins

In this paper, we generalize the concept of heavy-tailed multi-armed bandits to adversarial environments, and develop robust best-of-both-worlds algorithms for heavy-tailed multi-armed bandits (MAB), where losses have $\alpha$-th…

Machine Learning · Computer Science 2022-06-14 Jiatai Huang , Yan Dai , Longbo Huang

We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classical objective, recent work shows that even such algorithms…

Information Theory · Computer Science 2026-04-17 Subhodip Panda , Shubhada Agrawal

We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$,…

Machine Learning · Computer Science 2024-05-03 Bingshan Hu , Zhiming Huang , Tianyue H. Zhang , Mathias Lécuyer , Nidhi Hegde

Influence maximization, adaptive routing, and dynamic spectrum allocation all require choosing the right action from a large set of alternatives. Thanks to the advances in combinatorial optimization, these and many similar problems can be…

Machine Learning · Computer Science 2020-12-29 Alihan Hüyük , Cem Tekin

This paper studies bandit convex optimization in non-stationary environments with two-point feedback, using dynamic regret as the performance measure. We propose an algorithm based on bandit mirror descent that extends naturally to…

Optimization and Control · Mathematics 2026-05-26 Chang He , Bo Jiang , Shuzhong Zhang

Stochastic rising rested bandit (SRRB) is a setting where the arms' expected rewards increase as they are pulled. It models scenarios in which the performances of the different options grow as an effect of an underlying learning process…

Machine Learning · Statistics 2025-05-21 Marco Fiandri , Alberto Maria Metelli , Francesco Trovò