Context-dependent Ranking and Selection under a Bayesian Framework

TL;DR

This paper introduces a Bayesian framework for context-dependent ranking and selection, proposing a dynamic sampling scheme that efficiently identifies optimal designs across varying contexts.

Contribution

The paper develops a novel dynamic sampling scheme for context-dependent optimization within a Bayesian framework, with proven consistency and improved efficiency.

Findings

Significant efficiency improvements demonstrated in numerical experiments.

The proposed scheme is proven to be consistent.

Effective in selecting best designs across different contexts.

Abstract

We consider a context-dependent ranking and selection problem. The best design is not universal but depends on the contexts. Under a Bayesian framework, we develop a dynamic sampling scheme for context-dependent optimization (DSCO) to efficiently learn and select the best designs in all contexts. The proposed sampling scheme is proved to be consistent. Numerical experiments show that the proposed sampling scheme significantly improves the efficiency in context-dependent ranking and selection.