AI RESEARCH
Anytime and Difficulty-Adaptive PAC-Bayes for Constrained Density-Ratio Network with Continual Learning Guarantees
arXiv CS.LG
•
ArXi:2605.17212v1 Announce Type: new A unified framework for learning under covariate shift is presented, in which a constrained density-ratio network approximates the Radon-Nikodym derivative $r^\star = dP/dQ$ from source $Q$ to target $P$, s an importance-weighted empirical risk, and feeds an anytime PAC-Bayes generalization certificate.