Generalization Bounds for Markov Algorithms through Entropy Flow Computations
This work builds on a principled continuous-time approximation of Markov algorithms and introduces a new, exact entropy flow formula for such processes, and establishes novel connections to a well-studied family of modified logarithmic Sobolev inequalities.
Benjamin Dupuis, Maxime Haddouche, George Deligiannidis et al.
· 2 citations