Task-based End-to-end Model Learning in Stochastic Optimization

TL;DR

This paper introduces an end-to-end learning approach for probabilistic models that directly optimizes task-specific objectives in stochastic programming, demonstrated through inventory, grid scheduling, and energy arbitrage tasks.

Contribution

It presents a novel end-to-end training method that aligns model learning with ultimate task objectives in stochastic optimization contexts.

Findings

Outperforms traditional modeling approaches in experiments.

Outperforms black-box policy optimization methods.

Effective across diverse real-world applications.

Abstract

With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process. However, the criteria by which we train these algorithms often differ from the ultimate criteria on which we evaluate them. This paper proposes an end-to-end approach for learning probabilistic machine learning models in a manner that directly captures the ultimate task-based objective for which they will be used, within the context of stochastic programming. We present three experimental evaluations of the proposed approach: a classical inventory stock problem, a real-world electrical grid scheduling task, and a real-world energy storage arbitrage task. We show that the proposed approach can outperform both traditional modeling and purely black-box policy optimization approaches in these applications.