English
Related papers

Related papers: Asymptotically Optimal Information-Directed Sampli…

200 papers

Sharp asymptotic lower bounds of the expected quadratic variation of discretization error in stochastic integration are given. The theory relies on inequalities for the kurtosis and skewness of a general random variable which are themselves…

Probability · Mathematics 2012-04-04 Masaaki Fukasawa

Entropy maximization and free energy minimization are general physical principles for modeling the dynamics of various physical systems. Notable examples include modeling decision-making within the brain using the free-energy principle,…

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem. By introducing an entropy regularisation, we obtain a smooth asymptotic approximation to the value…

Optimization and Control · Mathematics 2022-09-07 Samuel N. Cohen , Tanut Treetanthiploet

We consider the infinite-horizon, average-reward restless bandit problem in discrete time. We propose a new class of policies that are designed to drive a progressively larger subset of arms toward the optimal distribution. We show that our…

Machine Learning · Computer Science 2026-03-31 Yige Hong , Qiaomin Xie , Yudong Chen , Weina Wang

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time…

Machine Learning · Statistics 2012-07-20 Emilie Kaufmann , Nathaniel Korda , Rémi Munos

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under…

Machine Learning · Computer Science 2020-03-03 Ahmadreza Moradipari , Sanae Amani , Mahnoosh Alizadeh , Christos Thrampoulidis

There has been a recent surge of interest in nonparametric bandit algorithms based on subsampling. One drawback however of these approaches is the additional complexity required by random subsampling and the storage of the full history of…

Artificial Intelligence · Computer Science 2021-06-22 Dorian Baudry , Yoan Russac , Olivier Cappé

Assuming that data are collected sequentially from independent streams, we consider the simultaneous testing of multiple binary hypotheses under two general setups; when the number of signals (correct alternatives) is known in advance, and…

Statistics Theory · Mathematics 2017-02-14 Yanglei Song , Georgios Fellouris

In this paper, we consider a class of continuous-time, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation methods and sampling-based algorithms for deterministic path planning,…

Robotics · Computer Science 2012-02-27 Vu Anh Huynh , Sertac Karaman , Emilio Frazzoli

We consider a large number of agents collaborating on a multi-armed bandit problem with a large number of arms. The goal is to minimise the regret of each agent in a communication-constrained setting. We present a decentralised algorithm…

Machine Learning · Computer Science 2021-09-21 Conor Newton , Ayalvadi Ganesh , Henry W. J. Reeve

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

Machine Learning · Computer Science 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

We develop a general theory to optimize the frequentist regret for sequential learning problems, where efficient bandit and reinforcement learning algorithms can be derived from unified Bayesian principles. We propose a novel optimization…

Machine Learning · Computer Science 2024-02-12 Yunbei Xu , Assaf Zeevi

Many real-world functions are defined over both categorical and category-specific continuous variables and thus cannot be optimized by traditional Bayesian optimization (BO) methods. To optimize such functions, we propose a new method that…

Machine Learning · Computer Science 2019-12-02 Dang Nguyen , Sunil Gupta , Santu Rana , Alistair Shilton , Svetha Venkatesh

Information-directed sampling (IDS) has revealed its potential as a data-efficient algorithm for reinforcement learning (RL). However, theoretical understanding of IDS for Markov Decision Processes (MDPs) is still limited. We develop novel…

Machine Learning · Computer Science 2022-11-28 Botao Hao , Tor Lattimore

Sequential decision-making algorithms such as multi-armed bandits can find optimal personalized decisions, but are notoriously sample-hungry. In personalized medicine, for example, training a bandit from scratch for every patient is…

Machine Learning · Computer Science 2026-05-12 Ahmet Zahid Balcıoğlu , Newton Mwai , Emil Carlsson , Fredrik D. Johansson

We study the problem of Gaussian bandits with general side information, as first introduced by Wu, Szepesvari, and Gyorgy. In this setting, the play of an arm reveals information about other arms, according to an arbitrary a priori known…

Machine Learning · Computer Science 2025-05-19 Alexia Atsidakou , Orestis Papadigenopoulos , Constantine Caramanis , Sujay Sanghavi , Sanjay Shakkottai

This paper is concerned with the optimal identification problem of dynamical systems in which only quantized output observations are available under the assumption of fixed thresholds and bounded persistent excitations. Based on a…

Systems and Control · Electrical Eng. & Systems 2023-09-12 Ying Wang , Yanlong Zhao , Ji-Feng Zhang

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

Adaptive importance sampling (AIS) uses past samples to update the \textit{sampling policy} $q_t$ at each stage $t$. Each stage $t$ is formed with two steps : (i) to explore the space with $n_t$ points according to $q_t$ and (ii) to exploit…

Statistics Theory · Mathematics 2018-10-04 Bernard Delyon , François Portier

We consider a finite-horizon multi-armed bandit (MAB) problem in a Bayesian setting, for which we propose an information relaxation sampling framework. With this framework, we define an intuitive family of control policies that include…

Machine Learning · Computer Science 2021-06-17 Seungki Min , Costis Maglaras , Ciamac C. Moallemi