Bayesian Design Principles for Frequentist Sequential Learning

We develop a general theory to optimize the frequentist regret for sequential learning problems, where efficient bandit and reinforcement learning algorithms can be derived from unified Bayesian principles. We propose a novel optimization approach to generate "algorithmic beliefs" at each...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Xu, Yunbei, Zeevi, Assaf
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.02.2024
Subjects
Algorithms
Bayesian analysis
Convexity
Machine learning
Multi-armed bandit problems
Nonstationary environments
Optimization
Principles
Online AccessGet full text

Cover

More Information
Summary:We develop a general theory to optimize the frequentist regret for sequential learning problems, where efficient bandit and reinforcement learning algorithms can be derived from unified Bayesian principles. We propose a novel optimization approach to generate "algorithmic beliefs" at each round, and use Bayesian posteriors to make decisions. The optimization objective to create "algorithmic beliefs," which we term "Algorithmic Information Ratio," represents an intrinsic complexity measure that effectively characterizes the frequentist regret of any algorithm. To the best of our knowledge, this is the first systematical approach to make Bayesian-type algorithms prior-free and applicable to adversarial settings, in a generic and optimal manner. Moreover, the algorithms are simple and often efficient to implement. As a major application, we present a novel algorithm for multi-armed bandits that achieves the "best-of-all-worlds" empirical performance in the stochastic, adversarial, and non-stationary environments. And we illustrate how these principles can be used in linear bandits, bandit convex optimization, and reinforcement learning.
ISSN:2331-8422