End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty
This work addresses fairness and robustness in AI and operations research decision models, representing an incremental extension of existing methods to new objective functions.
The paper tackles the challenge of integrating fairness and robustness into decision-making under uncertainty by extending the Predict-Then-Optimize paradigm to handle nondifferentiable Ordered Weighted Averaging objectives, enabling end-to-end learning for multiobjective optimization.
Many decision processes in artificial intelligence and operations research are modeled by parametric optimization problems whose defining parameters are unknown and must be inferred from observable data. The Predict-Then-Optimize (PtO) paradigm in machine learning aims to maximize downstream decision quality by training the parametric inference model end-to-end with the subsequent constrained optimization. This requires backpropagation through the optimization problem using approximation techniques specific to the problem's form, especially for nondifferentiable linear and mixed-integer programs. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives, known for their ability to ensure properties of fairness and robustness in decision models. Through a collection of training techniques and proposed application settings, it shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.