Skip to yearly menu bar Skip to main content


Poster

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

Priya Donti · J. Zico Kolter · Brandon Amos

Pacific Ballroom #205

Keywords: [ Stochastic Methods ] [ Predictive Models ] [ Optimization ] [ Decision and Control ] [ Planning ] [ Sustainability ]


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.

Live content is unavailable. Log in and register to view live content