Linear Models

These optimization problems are solved exactly (or approximately, e.g., kernel) through solvers.

See the f-divergence DRO notebook for standard and partial-shift linear examples.

See the Wasserstein DRO notebook for linear classification, regression, and robust-satisficing examples.

See the Group DRO notebook for an end-to-end linear and neural example.

See the kernel DRO notebook for an MMD-DRO example and ambiguity-set kernel selection guidance.

See the Bayesian DRO notebook for frequentist and Bayesian parametric examples.

See the mixed-distance DRO notebook for Sinkhorn, MOT, OR-WDRO, and Holistic DRO examples.