Fixed Confidence and Fixed Tolerance Bi-level Optimization for Selecting the Best Optimized System

TL;DR

This paper introduces a multi-stage framework for stochastic bi-level optimization that efficiently selects the best system under fixed confidence and tolerance constraints, applicable to model selection and design problems.

Contribution

It proposes a novel Pruning-Optimization framework that improves computational efficiency in fixed-confidence, fixed-tolerance bi-level optimization problems.

Findings

The framework guarantees statistical validity and sample complexity bounds.

Numerical experiments demonstrate improved efficiency over existing methods.

Abstract

In this paper, we study a fixed-confidence, fixed-tolerance formulation of a class of stochastic bi-level optimization problems, where the upper-level problem selects from a finite set of systems based on a performance metric, and the lower-level problem optimizes continuous decision variables for each system. Notably, the objective functions for the upper and lower levels can differ. This class of problems has a wide range of applications, including model selection, ranking and selection under input uncertainty, and optimal design. To address this, we propose a multi-stage Pruning-Optimization framework that alternates between comparing the performance of different systems (Pruning) and optimizing systems (Optimization). % In the Pruning stage, we design a sequential algorithm that identifies and eliminates inferior systems through systematic performance evaluations. In the Optimization stage, the goal is to solve for a near-optimal solution that meets specified confidence and tolerance requirements. This multi-stage framework is designed to enhance computational efficiency by pruning inferior systems with high tolerance early on, thereby avoiding unnecessary computational efforts. We demonstrate the effectiveness of the proposed algorithm through both theoretical analysis of statistical validity and sample complexity and numerical experiments.