mmd

USAD proposes two new statistics, Variance Discrepancy and Perturbation-based Covariance Discrepancy, to capture global and local uncertainty patterns of adversarial examples, achieving superior detection performance over baseline methods.

This paper introduces a difference-of-convex programming framework in Wasserstein space for optimizing non-convex functionals over probability measures, with explicit decompositions for Maximum Mean Discrepancy and Energy Distance, and proves convergence of the lifted convex-concave procedure.

Moment Matching Q-Learning (MoMa QL) uses maximum mean discrepancy to match all moment statistics for distribution-level convergence in offline RL, achieving computational efficiency and strong performance on D4RL tasks.

This paper develops a PAC-Bayesian framework for test-time adaptation that uses MMD-balls as credal sets, providing formal generalization bounds and separating epistemic from aleatoric uncertainty under distribution shift.