Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities

ArXi:2602.07999v3 Announce Type: replace-cross Change of measure inequalities translate divergences between probability measures into explicit bounds on event probabilities, and play an important role in deriving probabilistic guarantees in learning theory, information theory, and statistics. We propose novel change of measure inequalities via a unified framework based on the data processing inequality, which is surprisingly elementary yet powerful enough to yield novel, tighter inequalities.