Distributionally Robust Optimization via Targeted Integral Probability Metrics for General Data Processes

Distributionally robust optimization (DRO) has been successful in addressing decision-making problems under uncertainty when the underlying distribution is unknown. Existing data-driven DRO frameworks, however, often impose restrictive assumptions on the data-generating process. We propose a new DRO framework based on targeted integral probability metrics. The ambiguity set is defined directly through the loss functions induced … Read more

Pessimistic bilevel optimization approach for decision-focused learning

The recent interest in contextual optimization problems, where randomness is associated with side information, has led to two primary strategies for formulation and solution. The first, estimate-then-optimize, separates the estimation of the problem’s parameters from the optimization process. The second, decision-focused optimization, integrates the optimization problem’s structure directly into the prediction procedure. In this work, … Read more