English
Related papers

Related papers: Order Optimal Regret Bounds for Sharpe Ratio Optim…

200 papers

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 propose ${\tt AdaTS}$, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. The key idea in ${\tt AdaTS}$ is to adapt to an unknown task prior distribution by maintaining a distribution over its…

Machine Learning · Computer Science 2022-02-28 Soumya Basu , Branislav Kveton , Manzil Zaheer , Csaba Szepesvári

In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoot}). The \texttt{ReBoot} enforces exploration by injecting…

Machine Learning · Statistics 2020-02-21 Chi-Hua Wang , Yang Yu , Botao Hao , Guang Cheng

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

Mean rewards of actions are often correlated. The form of these correlations may be complex and unknown a priori, such as the preferences of a user for recommended products and their categories. To maximize statistical efficiency, it is…

Machine Learning · Computer Science 2022-02-04 Joey Hong , Branislav Kveton , Sumeet Katariya , Manzil Zaheer , Mohammad Ghavamzadeh

I study adversarial attacks against stochastic bandit algorithms. At each round, the learner chooses an arm, and a stochastic reward is generated. The adversary strategically adds corruption to the reward, and the learner is only able to…

Machine Learning · Computer Science 2024-03-18 Shiliang Zuo

We introduce a new stochastic smoothing perspective to study adversarial contextual bandit problems. We propose a general algorithm template that represents random perturbation based algorithms and identify several perturbation…

Machine Learning · Statistics 2019-06-12 Young Hun Jung , Ambuj Tewari

In the classical multi-armed bandit problem, d arms are available to the decision maker who pulls them sequentially in order to maximize his cumulative reward. Guarantees can be obtained on a relative quantity called regret, which scales…

Machine Learning · Computer Science 2017-06-06 Joon Kwon , Vianney Perchet , Claire Vernade

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

Machine Learning · Computer Science 2022-10-18 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi

Several sparsity-constrained algorithms such as Orthogonal Matching Pursuit or the Frank-Wolfe algorithm with sparsity constraints work by iteratively selecting a novel atom to add to the current non-zero set of variables. This selection…

Machine Learning · Computer Science 2016-08-23 A Rakotomamonjy , S Koço , Liva Ralaivola

The stochastic multi-armed bandit problem is a well-known model for studying the exploration-exploitation trade-off. It has significant possible applications in adaptive clinical trials, which allow for dynamic changes in the treatment…

Machine Learning · Computer Science 2019-06-11 Hossein Aboutalebi , Doina Precup , Tibor Schuster

We study the problem of minimizing gap-dependent regret for single-pass streaming stochastic multi-armed bandits (MAB). In this problem, the $n$ arms are present in a stream, and at most $m<n$ arms and their statistics can be stored in the…

Machine Learning · Computer Science 2025-03-05 Zichun Ye , Chihao Zhang , Jiahao Zhao

We consider the stochastic bandit problem with a continuous set of arms, with the expected reward function over the arms assumed to be fixed but unknown. We provide two new Gaussian process-based algorithms for continuous bandit…

Machine Learning · Computer Science 2017-05-18 Sayak Ray Chowdhury , Aditya Gopalan

We consider best arm identification in the multi-armed bandit problem. Assuming certain continuity conditions of the prior, we characterize the rate of the Bayesian simple regret. Differing from Bayesian regret minimization (Lai, 1987), the…

Machine Learning · Computer Science 2023-07-27 Junpei Komiyama , Kaito Ariu , Masahiro Kato , Chao Qin

We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent…

Machine Learning · Computer Science 2022-03-03 Julian Zimmert , Yevgeny Seldin

We consider the contextual bandit problem, where a player sequentially makes decisions based on past observations to maximize the cumulative reward. Although many algorithms have been proposed for contextual bandit, most of them rely on…

Machine Learning · Computer Science 2021-06-08 Qin Ding , Cho-Jui Hsieh , James Sharpnack

In Reinforcement Learning (RL), multi-armed Bandit (MAB) problems have found applications across diverse domains such as recommender systems, healthcare, and finance. Traditional MAB algorithms typically assume stationary reward…

Artificial Intelligence · Computer Science 2024-10-10 Gustavo de Freitas Fonseca , Lucas Coelho e Silva , Paulo André Lima de Castro

We study a widely used Bayesian optimization method, Gaussian process Thompson sampling (GP-TS), under the assumption that the objective function is a sample path from a GP. Compared with the GP upper confidence bound (GP-UCB) with…

Machine Learning · Statistics 2026-03-11 Shion Takeno , Shogo Iwazaki

We consider the stochastic linear contextual bandit problem with high-dimensional features. We analyze the Thompson sampling algorithm using special classes of sparsity-inducing priors (e.g., spike-and-slab) to model the unknown parameter…

Machine Learning · Statistics 2023-01-31 Sunrit Chakraborty , Saptarshi Roy , Ambuj Tewari

In this paper, we study the stochastic combinatorial multi-armed bandit (CMAB) framework that allows a general nonlinear reward function, whose expected value may not depend only on the means of the input random variables but possibly on…

Machine Learning · Computer Science 2018-07-23 Wei Chen , Wei Hu , Fu Li , Jian Li , Yu Liu , Pinyan Lu