Knowledge Gradient for Selection with Covariates: Consistency and Computation
Abstract
Knowledge gradient is a design principle for developing Bayesian sequential sampling policies to consider in this paper the ranking and selection problem in the presence of covariates, where the best alternative is not universal but depends on the covariates. In this context, we prove that under minimal assumptions, the sampling policy based on knowledge gradient is consistent, in the sense that following the policy the best alternative as a function of the covariates will be identified almost surly as the number of samples grows. We also propose a stochastic gradient ascent algorithm for computing the sampling policy and demonstrate its performance via numerical experiments.
Type
Publication
Naval Research Logistics 69(3):496–507
Authors
Professor in Department of Industrial and Systems Engineering at the University of Minnesota.
Authors
Associate Professor in the Sino-US Global Logistics Institute, Shanghai Jiao Tong University.
Authors
I am an Associate Professor at HKUST, jointly appointed in the Department of Industrial Engineering and Decision Analytics and the Department of Economics, and the Academic Director of the MSc in FinTech program. I serve as an Associate Editor for several leading journals in the field, including Management Science, Operations Research, Navel Research Logistics, and Queueing Systems.