paper-with-me

Papers

Information Directed Sampling for Sparse Linear Bandits

2021-05-29 · NeurIPS 2021 12 · Botao Hao, Tor Lattimore, Wei Deng

Stochastic sparse linear bandits offer a practical model for high-dimensional online decision-making problems and have a rich information-regret structure. In this work we explore the use of information-directed sampling (IDS), which naturally balances the information-regret trade-off. We develop a class of information-theoretic Bayesian regret bounds that nearly match existing lower bounds on a variety of problem instances, demonstrating the adaptivity of IDS. To efficiently implement sparse IDS, we propose an empirical Bayesian approach for sparse posterior sampling using a spike-and-slab Gaussian-Laplace prior. Numerical results demonstrate significant regret reductions by sparse IDS relative to several baselines.

📄 PDF Abstract BibTeX arXiv:2105.14267

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Contextual Information-Directed Sampling

2022-05-22 · Botao Hao, Tor Lattimore, Chao Qin

Information-directed sampling (IDS) has recently demonstrated its potential as a data-efficient reinforcement learning algorithm. However, it is still unclear what is the right form of information ratio to optimize when …

Multi-Armed BanditsReinforcement Learning (RL)

Sparse Optimistic Information Directed Sampling

2025-10-28 · Ludovic Schwartz, Hamish Flynn, Gergely Neu arxiv

Many high-dimensional online decision-making problems can be modeled as stochastic sparse linear bandits. Most existing algorithms are designed to achieve optimal worst-case regret in either the data-rich regime, where p…

Bias-Robust Bayesian Optimization via Dueling Bandits

2021-05-25 · Johannes Kirschner, Andreas Krause

We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueli…

Bayesian Optimization

Information Directed Sampling for Linear Partial Monitoring

2020-02-25 · Johannes Kirschner, Tor Lattimore, Andreas Krause

Partial monitoring is a rich framework for sequential decision making under uncertainty that generalizes many well known bandit models, including linear, combinatorial and dueling bandits. We introduce information direct…

Decision MakingDecision Making Under UncertaintySequential Decision Making

Information-Directed Sampling for Causal Bandits

2026-07-17 · Muhammad Qasim Elahi, Murat Kocaoglu, Mahsa Ghasemi arxiv

Causal bandits exploit structural relationships among variables to share information across interventions and accelerate the identification of high-reward decisions. In many applications, however, some variables cannot b…