English
Related papers

Related papers: A PAC algorithm in relative precision for bandit p…

200 papers

We consider the question introduced by \cite{Mason2020} of identifying all the $\varepsilon$-optimal arms in a finite stochastic multi-armed bandit with Gaussian rewards. We give two lower bounds on the sample complexity of any algorithm…

Machine Learning · Statistics 2022-04-07 Aymen Al Marjani , Tomáš Kocák , Aurélien Garivier

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

Machine Learning · Computer Science 2023-11-01 Reda Alami , Mohammed Mahfoud , Mastane Achab

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

We study the problem of estimating a continuous ability parameter from sequential binary responses by actively asking questions with varying difficulties, a setting that arises naturally in adaptive testing and online preference learning.…

Machine Learning · Statistics 2025-10-10 Sanghwa Kim , Dohyun Ahn , Seungki Min

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 consider the quantum version of the bandit problem known as {\em best arm identification} (BAI). We first propose a quantum modeling of the BAI problem, which assumes that both the learning agent and the environment are quantum; we then…

Machine Learning · Computer Science 2020-09-23 Balthazar Casalé , Giuseppe Di Molfetta , Hachem Kadri , Liva Ralaivola

In the stochastic knapsack problem, we are given a knapsack of size B, and a set of jobs whose sizes and rewards are drawn from a known probability distribution. However, we know the actual size and reward only when the job completes. How…

Data Structures and Algorithms · Computer Science 2011-02-21 Anupam Gupta , Ravishankar Krishnaswamy , Marco Molinaro , R. Ravi

Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to leverage a rank-1…

Machine Learning · Statistics 2021-08-03 Flore Sentenac , Jialin Yi , Clément Calauzènes , Vianney Perchet , Milan Vojnovic

We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even…

Machine Learning · Computer Science 2019-12-17 Weihao Kong , Gregory Valiant , Emma Brunskill

We consider the problem of sequentially choosing between a set of unbiased Monte Carlo estimators to minimize the mean-squared-error (MSE) of a final combined estimate. By reducing this task to a stochastic multi-armed bandit problem, we…

Artificial Intelligence · Computer Science 2014-05-15 James Neufeld , András György , Dale Schuurmans , Csaba Szepesvári

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible…

Machine Learning · Statistics 2018-06-07 Zalán Borsos , Andreas Krause , Kfir Y. Levy

We study the linear contextual bandit problem in the presence of adversarial corruption, where the reward at each round is corrupted by an adversary, and the corruption level (i.e., the sum of corruption magnitudes over the horizon) is…

Machine Learning · Computer Science 2022-07-12 Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

We consider a stochastic continuum armed bandit problem where the arms are indexed by the $\ell_2$ ball $B_{d}(1+\nu)$ of radius $1+\nu$ in $\mathbb{R}^d$. The reward functions $r :B_{d}(1+\nu) \rightarrow \mathbb{R}$ are considered to…

Machine Learning · Statistics 2017-05-31 Hemant Tyagi , Sebastian Stich , Bernd Gärtner

In linear contextual bandits, the objective is to select actions that maximize cumulative rewards, modeled as a linear function with unknown parameters. Although Thompson Sampling performs well empirically, it does not achieve optimal…

Machine Learning · Statistics 2025-06-18 Wonyoung Kim

We propose algorithms based on a multi-level Thompson sampling scheme, for the stochastic multi-armed bandit and its contextual variant with linear expected rewards, in the setting where arms are clustered. We show, both theoretically and…

Machine Learning · Computer Science 2022-06-16 Emil Carlsson , Devdatt Dubhashi , Fredrik D. Johansson

In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et al. (2010) and improve on their results using a new…

Machine Learning · Statistics 2025-02-18 Amaury Gouverneur , Tobias J. Oechtering , Mikael Skoglund

We present an algorithm, "constrained successive accept or reject (CSAR)," for the problem of identifying the subset of top feasible-arms from a given finite set of arms with the limited sampling-budget equal to a given time-horizon when…

Optimization and Control · Mathematics 2025-01-22 Hyeong Soo Chang

We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing…

Machine Learning · Computer Science 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

In the context of stochastic continuum-armed bandits, we present an algorithm that adapts to the unknown smoothness of the objective function. We exhibit and compute a polynomial cost of adaptation to the H{\"o}lder regularity for regret…

Machine Learning · Statistics 2019-12-10 Hédi Hadiji

Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. We propose a simple policy,…

Statistics Theory · Mathematics 2016-03-30 Vianney Perchet , Philippe Rigollet , Sylvain Chassang , Erik Snowberg