TY - GEN
T1 - Learning Joint Models of Prediction and Optimization
AU - Kotary, James
AU - Di Vito, Vincenzo
AU - Christopher, Jacob
AU - Van Hentenryck, Pascal
AU - Fioretto, Ferdinando
N1 - Publisher Copyright:
© 2024 The Authors.
PY - 2024/10/16
Y1 - 2024/10/16
N2 - The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from exogenous features before solving. This setting is common to many real-world decision processes, and recently it has been shown that decision quality can be substantially improved by solving and differentiating the optimization problem within an end-to-end training loop. However, this approach requires significant computational effort in addition to handcrafted, problem-specific rules for backpropagation through the optimization step, challenging its applicability to a broad class of optimization problems. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models. The approach is generic, and based on an 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 and accurate solutions to an array of challenging Predict-Then-Optimize problems.
AB - The Predict-Then-Optimize framework uses machine learning models to predict unknown parameters of an optimization problem from exogenous features before solving. This setting is common to many real-world decision processes, and recently it has been shown that decision quality can be substantially improved by solving and differentiating the optimization problem within an end-to-end training loop. However, this approach requires significant computational effort in addition to handcrafted, problem-specific rules for backpropagation through the optimization step, challenging its applicability to a broad class of optimization problems. This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models. The approach is generic, and based on an 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 and accurate solutions to an array of challenging Predict-Then-Optimize problems.
UR - http://www.scopus.com/inward/record.url?scp=85213355575&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85213355575&partnerID=8YFLogxK
U2 - 10.3233/FAIA240775
DO - 10.3233/FAIA240775
M3 - Conference contribution
AN - SCOPUS:85213355575
T3 - Frontiers in Artificial Intelligence and Applications
SP - 2476
EP - 2483
BT - ECAI 2024 - 27th European Conference on Artificial Intelligence, Including 13th Conference on Prestigious Applications of Intelligent Systems, PAIS 2024, Proceedings
A2 - Endriss, Ulle
A2 - Melo, Francisco S.
A2 - Bach, Kerstin
A2 - Bugarin-Diz, Alberto
A2 - Alonso-Moral, Jose M.
A2 - Barro, Senen
A2 - Heintz, Fredrik
PB - IOS Press BV
T2 - 27th European Conference on Artificial Intelligence, ECAI 2024
Y2 - 19 October 2024 through 24 October 2024
ER -