Ensemble sampling for linear bandits: small ensembles suffice

2023-11-14 · David Janz, Alexander E. Litvak, Csaba Szepesvári

We provide the first useful and rigorous analysis of ensemble sampling for the stochastic linear bandit setting. In particular, we show that, under standard assumptions, for a $d$-dimensional stochastic linear bandit with an interaction horizon $T$, ensemble sampling with an ensemble of size of order $d \log T$ incurs regret at most of the order $(d \log T)^{5/2} \sqrt{T}$. Ours is the first result in any structured setting not to require the size of the ensemble to scale linearly with $T$ -- which defeats the purpose of ensemble sampling -- while obtaining near $\smash{\sqrt{T}}$ order regret. Our result is also the first to allow for infinite action sets.

📄 PDF Abstract BibTeX arXiv:2311.08376

Code (0)

등록된 구현이 없습니다.

Tree Ensembles for Contextual Bandits

2024-02-10 · Hannes Nilsson, Rikard Johansson, Niklas Åkerblom, Morteza Haghir Chehreghani

We propose a new framework for contextual multi-armed bandits based on tree ensembles. Our framework adapts two widely used bandit methods, Upper Confidence Bound and Thompson Sampling, for both standard and combinatoria…

Multi-Armed Bandits Thompson Sampling

Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits

2025-10-12 · Jiazheng Sun, Weixin Wang, Pan Xu arxiv

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemb…

Sharp analysis of linear ensemble sampling

2026-02-08 · David Janz, Arya Akhavan, Csaba Szepesvári arxiv

We analyse linear ensemble sampling (ES) with standard Gaussian perturbations in stochastic linear bandits. We show that for ensemble size $m=Θ(d\log n)$, ES attains $\tilde O(d^{3/2}\sqrt n)$ high-probability regret, cl…

JAMUN: Transferable Molecular Conformational Ensemble Generation with Walk-Jump Sampling

2024-10-18 · Ameya Daigavane, Bodhi P. Vani, Saeed Saremi, Joseph Kleinhenz 외

Conformational ensembles of protein structures are immensely important both to understanding protein function, and for drug discovery in novel modalities such as cryptic pockets. Current techniques for sampling ensembles…

Drug Discovery

Hypermodels for Exploration

2020-06-12 · ICLR 2020 1 · Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband 외

We study the use of hypermodels to represent epistemic uncertainty and guide exploration. This generalizes and extends the use of ensembles to approximate Thompson sampling. The computational cost of training an ensemble…

Thompson Sampling