3 papers
cs.LG2025
Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport
Jayadev Naram, Fredrik Hellström, Ziming Wang +2
In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setti…
cs.LG2024
Generalization Bounds: Perspectives from Information Theory and PAC-Bayes
Fredrik Hellström, Giuseppe Durisi, Benjamin Guedj +1
A fundamental question in theoretical machine learning is generalization. Over the past decades, the PAC-Bayesian approach has been established as a flexible framework to address t…
cs.LG2024
Comparing Comparators in Generalization Bounds
Fredrik Hellström, Benjamin Guedj
We derive generic information-theoretic and PAC-Bayesian generalization bounds involving an arbitrary convex comparator function, which measures the discrepancy between the trainin…