The framework interprets MMD-balls as credal sets to derive MMD-parameterized PAC-Bayesian generalization bounds and separate epistemic from aleatoric uncertainty in test-time adaptation.
PAC-Bayesian generalisation error bounds for Gaussian process classification.Journal of Machine Learning Research, 3:233–269
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
The framework interprets MMD-balls as credal sets to derive MMD-parameterized PAC-Bayesian generalization bounds and separate epistemic from aleatoric uncertainty in test-time adaptation.