PAC-Bayes bounds for Gibbs posteriors are obtained via singular learning theory, producing explicit and tighter posterior-averaged risk bounds that adapt to data structure in overparameterized models.
arXiv preprint arXiv:2501.12747 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory
PAC-Bayes bounds for Gibbs posteriors are obtained via singular learning theory, producing explicit and tighter posterior-averaged risk bounds that adapt to data structure in overparameterized models.