SimPO: Simultaneous Prediction and Optimization

TL;DR

SimPO introduces a joint framework that integrates predictive modeling and optimization into a single end-to-end process, improving decision quality by aligning predictions with optimization goals.

Contribution

It proposes a novel joint loss function for simultaneous prediction and optimization, enabling end-to-end training of models directly aligned with decision objectives.

Findings

Enhanced decision quality through joint training

End-to-end gradient-based optimization approach

Unified framework reduces sub-optimal solutions

Abstract

Many machine learning (ML) models are integrated within the context of a larger system as part of a key component for decision making processes. Concretely, predictive models are often employed in estimating the parameters for the input values that are utilized for optimization models as isolated processes. Traditionally, the predictive models are built first, then the model outputs are used to generate decision values separately. However, it is often the case that the prediction values that are trained independently of the optimization process produce sub-optimal solutions. In this paper, we propose a formulation for the Simultaneous Prediction and Optimization (SimPO) framework. This framework introduces the use of a joint weighted loss of a decision-driven predictive ML model and an optimization objective function, which is optimized end-to-end directly through gradient-based methods.