Data-driven decision-focused surrogate modeling

TL;DR

This paper presents a novel data-driven framework for creating decision-focused surrogate models that are simpler and more accurate in predicting optimal decisions for complex nonlinear optimization problems, especially in real-time applications.

Contribution

The paper introduces a bilevel programming approach for learning surrogate models that directly minimize decision prediction error, improving data efficiency and decision accuracy over standard methods.

Findings

Significantly more data-efficient than traditional surrogate modeling methods.

Produces simple, convex surrogate models with high decision prediction accuracy.

Validated on nonlinear chemical process optimization problems.

Abstract

We introduce the concept of decision-focused surrogate modeling for solving computationally challenging nonlinear optimization problems in real-time settings. The proposed data-driven framework seeks to learn a simpler, e.g. convex, surrogate optimization model that is trained to minimize the decision prediction error, which is defined as the difference between the optimal solutions of the original and the surrogate optimization models. The learning problem, formulated as a bilevel program, can be viewed as a data-driven inverse optimization problem to which we apply a decomposition-based solution algorithm from previous work. We validate our framework through numerical experiments involving the optimization of common nonlinear chemical processes such as chemical reactors, heat exchanger networks, and material blending systems. We also present a detailed comparison of decision-focused surrogate modeling with standard data-driven surrogate modeling methods and demonstrate that our approach is significantly more data-efficient while producing simple surrogate models with high decision prediction accuracy.