Timezone: »
Poster
Information Directed Sampling for Sparse Linear Bandits
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.
Author Information
Botao Hao (Deepmind)
Tor Lattimore (DeepMind)
Wei Deng (Purdue University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Spotlight: Information Directed Sampling for Sparse Linear Bandits »
Dates n/a. Room
More from the Same Authors
-
2021 Spotlight: Variational Bayesian Optimistic Sampling »
Brendan O'Donoghue · Tor Lattimore -
2022 Poster: The Neural Testbed: Evaluating Joint Predictions »
Ian Osband · Zheng Wen · Seyed Mohammad Asghari · Vikranth Dwaracherla · Xiuyuan Lu · MORTEZA IBRAHIMI · Dieterich Lawson · Botao Hao · Brendan O'Donoghue · Benjamin Van Roy -
2022 Poster: Regret Bounds for Information-Directed Reinforcement Learning »
Botao Hao · Tor Lattimore -
2021 Poster: Variational Bayesian Optimistic Sampling »
Brendan O'Donoghue · Tor Lattimore -
2021 Poster: Bandit Phase Retrieval »
Tor Lattimore · Botao Hao -
2020 Poster: High-Dimensional Sparse Linear Bandits »
Botao Hao · Tor Lattimore · Mengdi Wang -
2020 Poster: A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions »
Wei Deng · Guang Lin · Faming Liang -
2020 Poster: Model Selection in Contextual Stochastic Bandit Problems »
Aldo Pacchiano · My Phan · Yasin Abbasi Yadkori · Anup Rao · Julian Zimmert · Tor Lattimore · Csaba Szepesvari -
2020 Poster: Gaussian Gated Linear Networks »
David Budden · Adam Marblestone · Eren Sezener · Tor Lattimore · Gregory Wayne · Joel Veness -
2019 Poster: Bootstrapping Upper Confidence Bound »
Botao Hao · Yasin Abbasi Yadkori · Zheng Wen · Guang Cheng -
2019 Poster: A Geometric Perspective on Optimal Representations for Reinforcement Learning »
Marc Bellemare · Will Dabney · Robert Dadashi · Adrien Ali Taiga · Pablo Samuel Castro · Nicolas Le Roux · Dale Schuurmans · Tor Lattimore · Clare Lyle -
2019 Poster: An Adaptive Empirical Bayesian Method for Sparse Deep Learning »
Wei Deng · Xiao Zhang · Faming Liang · Guang Lin -
2019 Poster: Connections Between Mirror Descent, Thompson Sampling and the Information Ratio »
Julian Zimmert · Tor Lattimore