This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Greedy inference with structure-exploiting lazy maps

Michael Brennan, Daniele Bigoni, Olivier Zahm, Alessio Spantini, Youssef Marzouk

Oral presentation: Orals & Spotlights Track 25: Probabilistic Models/Statistics
on 2020-12-10T06:30:00-08:00 - 2020-12-10T06:45:00-08:00
Poster Session 6 (more posters)
on 2020-12-10T09:00:00-08:00 - 2020-12-10T11:00:00-08:00
Abstract: We propose a framework for solving high-dimensional Bayesian inference problems using \emph{structure-exploiting} low-dimensional transport maps or flows. These maps are confined to a low-dimensional subspace (hence, lazy), and the subspace is identified by minimizing an upper bound on the Kullback--Leibler divergence (hence, structured). Our framework provides a principled way of identifying and exploiting low-dimensional structure in an inference problem. It focuses the expressiveness of a transport map along the directions of most significant discrepancy from the posterior, and can be used to build deep compositions of lazy maps, where low-dimensional projections of the parameters are iteratively transformed to match the posterior. We prove weak convergence of the generated sequence of distributions to the posterior, and we demonstrate the benefits of the framework on challenging inference problems in machine learning and differential equations, using inverse autoregressive flows and polynomial maps as examples of the underlying density estimators.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.