Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 441 - Novel Statistical and Machine Learning Approaches for Business and Financial Services
Type: Topic Contributed
Date/Time: Thursday, August 6, 2020 : 10:00 AM to 11:50 AM
Sponsor: Section on Statistical Computing
Abstract #314032
Title: An Adaptive Algorithm to Multi-Armed Bandit Problem with High-Dimensional Covariates
Author(s): Wei Qian* and Ching-Kang Ing and Ji Liu
Companies: University of Delaware and National Tsing Hua University and University of Rochester
Keywords: contextual bandits; exploration-exploitation tradeoff; high-dimensional regression model; sequential decision making; stepwise regression procedure
Abstract:

This paper studies an important sequential decision making problem known as the multi-armed bandit problem with covariates. Under a linear bandit framework with high-dimensional covariates, we propose a general multi-stage arm allocation algorithm that integrates both arm elimination and randomized assignment strategies. By employing a class of high-dimensional regression methods for coefficient estimation, the proposed algorithm is shown to have near optimal finite-time regret performance under a new study scope. Based on synergistically verified benefit of a margin condition, our algorithm also exhibits an adaptive performance that automatically adapts to the margin and attains the optimal regret rates, up to a logarithmic factor. Besides the desirable regret performance, the proposed algorithm simultaneously generates useful coefficient estimation output for competitive arms and is shown to achieve both estimation consistency and variable selection consistency. Promising empirical performance is demonstrated through an online service example.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program