Dave Blei: "Black Box Variational Inference"

A core problem in statistics and machine learning is to approximate
difficult-to-compute probability distributions. This problem is
especially important in probabilistic modeling, which frames all
inference about unknown quantities as a calculation about a
conditional distribution. In this talk I present black box variational
inference (BBVI), a method a that approximates probability
distributions through optimization. BBVI easily applies to many
models but requires minimal mathematical work to implement. I will
demonstrate BBVI on deep exponential families---a method for Bayesian deep learning---and describe how it enables powerful tools for probabilistic programming.