English
Related papers

Related papers: Diffusion Approximations for Thompson Sampling in …

200 papers

We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might…

Machine Learning · Statistics 2015-04-01 Aditya Gopalan , Shie Mannor

In this paper we study a multi-arm bandit problem in which the quality of each arm is measured by the Conditional Value at Risk (CVaR) at some level alpha of the reward distribution. While existing works in this setting mainly focus on…

Machine Learning · Computer Science 2022-03-22 Dorian Baudry , Romain Gautron , Emilie Kaufmann , Odalric-Ambryn Maillard

We consider the problem of minimizing a sum of $n$ functions over a convex parameter set $\mathcal{C} \subset \mathbb{R}^p$ where $n\gg p\gg 1$. In this regime, algorithms which utilize sub-sampling techniques are known to be effective. In…

Machine Learning · Statistics 2015-12-03 Murat A. Erdogdu , Andrea Montanari

Linear diffusion processes serve as canonical continuous-time models for dynamic decision-making under uncertainty. These systems evolve according to drift matrices that specify the instantaneous rates of change in the expected system…

Machine Learning · Computer Science 2025-06-10 Mohamad Kazem Shirani Faradonbeh , Sadegh Shirani , Mohsen Bayati

We address online combinatorial optimization when the player has a prior over the adversary's sequence of losses. In this framework, Russo and Van Roy proposed an information-theoretic analysis of Thompson Sampling based on the information…

Machine Learning · Computer Science 2022-04-05 Sébastien Bubeck , Mark Sellke

We consider a continuous-time multi-arm bandit problem (CTMAB), where the learner can sample arms any number of times in a given interval and obtain a random reward from each sample, however, increasing the frequency of sampling incurs an…

Machine Learning · Computer Science 2023-04-20 Rahul Vaze , Manjesh K. Hanawal

In computational science workflows, it is often the case that 1) objective functions for optimization involve multiple simulation outputs, and 2) those simulations can be performed (at least partially) in parallel. In this work, we…

Optimization and Control · Mathematics 2026-05-28 Matt Menickelly

Stochastic policies (also known as relaxed controls) are widely used in continuous-time reinforcement learning algorithms. However, executing a stochastic policy and evaluating its performance in a continuous-time environment remain open…

Machine Learning · Computer Science 2025-10-03 Yanwei Jia , Du Ouyang , Yufei Zhang

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

Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. Unlike other…

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that the stochastic…

Machine Learning · Computer Science 2025-02-12 Jincheng Mei , Bo Dai , Alekh Agarwal , Sharan Vaswani , Anant Raj , Csaba Szepesvari , Dale Schuurmans

The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies exploration-exploitation tradeoff. Standard formulations exclude risk in decision making. Risknotably complicates the basic reward-maximising…

Machine Learning · Computer Science 2021-05-17 Ming Liang Ang , Eloise Y. Y. Lim , Joel Q. L. Chang

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

Given a set of arms $\mathcal{Z}\subset \mathbb{R}^d$ and an unknown parameter vector $\theta_\ast\in\mathbb{R}^d$, the pure exploration linear bandit problem aims to return $\arg\max_{z\in \mathcal{Z}} z^{\top}\theta_{\ast}$, with high…

Machine Learning · Statistics 2023-10-26 Zhaoqi Li , Kevin Jamieson , Lalit Jain

The multi-armed bandit (MAB) model is one of the most classical models to study decision-making in an uncertain environment. In this model, a player chooses one of $K$ possible arms of a bandit machine to play at each time step, where the…

Machine Learning · Computer Science 2023-06-13 Bo Li , Chi Ho Yeung

In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by Neu et al. and their concept of lifted information ratio. First, we prove a comprehensive bound on…

Machine Learning · Statistics 2023-04-27 Amaury Gouverneur , Borja Rodríguez-Gálvez , Tobias J. Oechtering , Mikael Skoglund

Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thompson Sampling (TS) is…

Machine Learning · Computer Science 2026-02-03 Zhenyu Zhao , David Zhang , Ellie Zhao , Ehsan Saberian

We study the multi-objective linear contextual bandit problem, where multiple possible conflicting objectives must be optimized simultaneously. We propose \texttt{MOL-TS}, the \textit{first} Thompson Sampling algorithm with Pareto regret…

Machine Learning · Statistics 2025-12-02 Somangchan Park , Heesang Ann , Min-hwan Oh

This letter proposes a linear bandit-based beam training framework for near-field communication under multi-path channels. By leveraging Thompson Sampling (TS), the framework adaptively balances exploration and exploitation to maximize…

Signal Processing · Electrical Eng. & Systems 2026-03-11 Junchi Liu , Zijun Wang , Rui Zhang

The theory of stochastic approximations form the theoretical foundation for studying convergence properties of many popular recursive learning algorithms in statistics, machine learning and statistical physics. Large deviations for…

Probability · Mathematics 2025-02-05 Henrik Hult , Adam Lindhe , Pierre Nyquist , Guo-Jhen Wu