Predict-then-Optimize via Learning to Optimize from Features

James Kotary, Vincenzo Di Vito Francesco, Jacob K Christopher, Pascal Van Hentenryck, Ferdinando Fioretto

Keywords: Predict-the-optimize, Learning to Optimize, ML and Optimization

TL;DR: We propose a method to solve predict and optimize problems under the lenses of learning to optimize

Abstract:

Many real-world decision processes are modeled by optimization problems whose defining parameters are unknown and must be inferred from observable data.
The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving. Recent works show that decision quality can be improved in this setting by solving and differentiating the optimization problem in the training loop, enabling end-to-end training with loss functions defined directly on the resulting decisions. However, this approach can be inefficient and requires handcrafted, problem-specific rules for backpropagation through the optimization step. This paper proposes an alternative approach, in which optimal solutions are learned directly from the observable features by predictive models. The approach is generic and based on a simple adaptation of the Learning-to-Optimize paradigm from which a rich variety of existing techniques can be employed. Experimental evaluations show the ability of several Learning-to-Optimize methods to provide efficient, accurate, and flexible solutions to an array of challenging Predict-Then-Optimize problems.

Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2627