Research
Optimal Transport PAC-Bayes Bounds
arXiv:2610.16560v1 Announce Type: new Abstract: PAC-Bayesian generalization bounds are among the strongest distribution-dependent guarantees in statistical learning and are typically expressed in term
arXiv:2610.16560v1 Announce Type: new Abstract: PAC-Bayesian generalization bounds are among the strongest distribution-dependent guarantees in statistical learning and are typically expressed in terms of the Kullback-Leibler (KL) divergence between a prior and posterior distribution. While analytically convenient, the KL divergence requires the posterior to be absolutely continuous w.r.t. the prior, imposing support constraints that can substantially restrict the choice of posterior. Moreover, the KL divergence does not account for the underlying geometry of the probability space. In this work, we derive new PAC-Bayesian bounds replacing the KL divergence with general optimal transport (OT) distances, including the total variation and Wasserstein-p distances.
Related
- PAC-Bayesian Certificates for Quadratic Closed-Loop Control
- Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
- Learning the Geometry of Collider Events with Metric-Aware Deep Sets
- Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport
Source: arXiv cs.LG | 2026-10-14