Transport, Variational Inference and Diffusions | Francisco Vargas скачать в хорошем качестве

Transport, Variational Inference and Diffusions | Francisco Vargas

Valence Portal is the home of the AI for drug discovery community. Join for more details on this talk and to connect with the speakers: https://portal.valencelabs.com/logg Abstract: This paper explores the connections between optimal transport and variational inference, with a focus on forward and reverse time stochastic differential equations and Girsanov transformations.We present a principled and systematic framework for sampling and generative modelling centred around divergences on path space. Our work culminates in the development of a novel score-based annealed flow technique (with connections to Jarzynski and Crooks identities from statistical physics) and a regularised iterative proportional fitting (IPF)-type objective, departing from the sequential nature of standard IPF. Through a series of generative modelling examples and a double-well-based rare event task, we showcase the potential of the proposed methods. Speaker: Francisco Vargas Twitter Hannes:   / hannesstaerk   Twitter Dominique:   / dom_beaini   ~ Chapters 00:00 - Intro + Motivation 08:22 - The Sampling Problem 09:11 - Hierarchical VAEs 16:25 - Entropic Optimal Transport 19:30 - Score-based Annealing 44:24 - Learning Forward and Backward Transitions 50:20 - Q&A