Learning to optimize via information-directed sampling

Daniel Russo, Benjamin Van Roy

Research output: Contribution to journalConference articlepeer-review

33 Scopus citations

Abstract

We propose information-directed sampling - a new algorithm for online optimization problems in which a decision-maker must balance between exploration and exploitation while learning from partial feedback. Each action is sampled in a manner that minimizes the ratio between the square of expected single-period regret and a measure of information gain: the mutual information between the optimal action and the next observation. We establish an expected regret bound for information-directed sampling that applies across a very general class of models and scales with the entropy of the optimal action distribution. For the widely studied Bernoulli and linear bandit models, we demonstrate simulation performance surpassing popular approaches, including upper confidence bound algorithms, Thompson sampling, and knowledge gradient. Further, we present simple analytic examples illustrating that information-directed sampling can dramatically outperform upper confidence bound algorithms and Thompson sampling due to the way it measures information gain.

Original languageEnglish (US)
Pages (from-to)1583-1591
Number of pages9
JournalAdvances in Neural Information Processing Systems
Volume2
Issue numberJanuary
StatePublished - Jan 1 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Learning to optimize via information-directed sampling'. Together they form a unique fingerprint.

Cite this