English
Related papers

Related papers: Deep Bandits Show-Off: Simple and Efficient Explor…

200 papers

A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing. The dependence of the arm choice on the past context and reward pairs compounds the…

Machine Learning · Statistics 2023-05-02 Wonyoung Kim , Gi-soo Kim , Myunghee Cho Paik

We propose feature perturbation, a simple yet effective exploration strategy for contextual bandits that injects randomness directly into feature inputs, instead of randomizing unknown parameters or adding noise to rewards. Remarkably, this…

Machine Learning · Computer Science 2025-10-27 Seouh-won Yi , Min-hwan Oh

In this paper, the causal bandit problem is investigated, with the objective of maximizing the long-term reward by selecting an optimal sequence of interventions on nodes in an unknown causal graph. It is assumed that both the causal…

Machine Learning · Computer Science 2025-06-30 Chen Peng , Di Zhang , Urbashi Mitra

The Bayesian paradigm offers principled tools for sequential decision-making under uncertainty, but its reliance on a probabilistic model for all parameters can hinder the incorporation of complex structural constraints. We introduce a…

Machine Learning · Computer Science 2025-10-09 Kaizheng Wang

Asynchronous Bayesian optimization is widely used for gradient-free optimization in domains with independent parallel experiments and varying evaluation times. Existing methods posit that standard acquisitions lead to redundant and repeated…

Machine Learning · Statistics 2026-03-17 Ben Riegler , James Odgers , Vincent Fortuin

Multi-armed bandits (MAB) are extensively studied in various settings where the objective is to \textit{maximize} the actions' outcomes (i.e., rewards) over time. Since safety is crucial in many real-world problems, safe versions of MAB…

Machine Learning · Computer Science 2021-12-14 Ilker Demirel , Mehmet Ufuk Ozdemir , Cem Tekin

We are often interested in identifying the feasible subset of a decision space under multiple constraints to permit effective design exploration. If determining feasibility required computationally expensive simulations, the cost of…

Machine Learning · Computer Science 2020-06-25 Alma Rahat , Michael Wood

Thompson sampling is a popular algorithm for solving multi-armed bandit problems, and has been applied in a wide range of applications, from website design to portfolio optimization. In such applications, however, the number of choices (or…

Methodology · Statistics 2021-01-19 Simon Mak , Yuanshuo Zhou , Lavonne Hoang , C. F. Jeff Wu

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

Recent growing adoption of experimentation in practice has led to a surge of attention to multiarmed bandits as a technique to reduce the opportunity cost of online experiments. In this setting, a decision-maker sequentially chooses among a…

Machine Learning · Computer Science 2022-04-04 Nima Hamidi , Mohsen Bayati

The topic of deep learning has seen a surge of interest in recent years both within and outside of the field of Statistics. Deep models leverage both nonlinearity and interaction effects to provide superior predictions in many cases when…

Methodology · Statistics 2020-09-18 Paul A. Parker , Scott H. Holan

Standard bandit algorithms that assume continual reallocation of measurement effort are challenging to implement due to delayed feedback and infrastructural/organizational difficulties. Motivated by practical instances involving a handful…

Machine Learning · Computer Science 2023-08-16 Ethan Che , Hongseok Namkoong

This paper addresses the challenge of model uncertainty in quantitative finance, where decisions in portfolio allocation, derivative pricing, and risk management rely on estimating stochastic models from limited data. In practice, the…

Computational Finance · Quantitative Finance 2025-06-10 Hans Buehler , Blanka Horvath , Yannick Limmer , Thorsten Schmidt

Identifying the parameters of a model and rating competitive models based on measured data has been among the most important but challenging topics in modern science and engineering, with great potential of application in structural system…

Computation · Statistics 2017-08-02 F. A. DiazDelaO , A. Garbuno-Inigo , S. K. Au , I. Yoshida

Exploration is a crucial aspect of bandit and reinforcement learning algorithms. The uncertainty quantification necessary for exploration often comes from either closed-form expressions based on simple models or resampling and posterior…

Machine Learning · Computer Science 2021-10-07 James McInerney , Nathan Kallus

In this paper, we study the non-asymptotic sample complexity for the pure exploration problem in contextual bandits and tabular reinforcement learning (RL): identifying an epsilon-optimal policy from a set of policies with high probability.…

Machine Learning · Computer Science 2024-06-12 Adhyyan Narang , Andrew Wagenmaker , Lillian Ratliff , Kevin Jamieson

Many real-world bandit applications are characterized by sparse rewards, which can significantly hinder learning efficiency. Leveraging problem-specific structures for careful distribution modeling is recognized as essential for improving…

Machine Learning · Statistics 2025-02-04 Haoyu Wei , Runzhe Wan , Lei Shi , Rui Song

Online learning in large-scale structured bandits is known to be challenging due to the curse of dimensionality. In this paper, we propose a unified meta-learning framework for a general class of structured bandit problems where the…

Machine Learning · Computer Science 2022-03-01 Runzhe Wan , Lin Ge , Rui Song

We consider bandits with anytime knapsacks (BwAK), a novel version of the BwK problem where there is an \textit{anytime} cost constraint instead of a total cost budget. This problem setting introduces additional complexities as it mandates…

Machine Learning · Computer Science 2025-01-31 Eray Can Elumar , Cem Tekin , Osman Yagan

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a…

Machine Learning · Computer Science 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari