Predict-Then-Optimize by Proxy: Learning Joint Models of Prediction and Optimization
This work addresses the need for more efficient and generic decision-making processes in real-world optimization problems, representing an incremental improvement over existing methods.
The paper tackles the inefficiency and problem-specific requirements of the Predict-Then-Optimize framework by proposing a generic method that learns optimal solutions directly from features using Learning-to-Optimize techniques, achieving efficient, accurate, and flexible solutions across various challenging problems.
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 method, in which optimal solutions are learned directly from the observable features by 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, accurate, and flexible solutions to an array of challenging Predict-Then-Optimize problems.