涩里番

听

This听seminar will feature Bogdan Mazoure, who will tell us about variational auto-encoders.

Abstract:

In many statistical inference scenarios, it is computationally inefficient or even impossible to calculate听the true solution to a given problem. Instead, we select a听class of approximate distributions (for example, Normal) and minimize the divergence between the true and听approximate solutions through maximization of a lower bound. Variational Bayesian methods are based on the free energy minimization听principle used to explain physical systems and have a number of advantages over traditional inference models.听In this talk, we will go over the main idea of approximate inference and discuss a neat use of variational inference in deep learning via variational auto-encoders.