Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Optimal Transport PAC-Bayes Bounds
Armin Beck, Peter Ochs, Jalal Fadili
PAC-Bayesian generalization bounds are among the strongest distribution-dependent guarantees in statistical learning and are typically expressed in terms of the Kullback-Leibler (K…
cs.LG2025
Symmetries in PAC-Bayesian Learning
Armin Beck, Peter Ochs
Symmetries are known to improve the empirical performance of machine learning models, yet theoretical guarantees explaining these gains remain limited. Prior work has focused mainl…