Theses Doctoral

Probabilistic Programming for Deep Learning

Tran, Dustin

We propose the idea of deep probabilistic programming, a synthesis of advances for systems at the intersection of probabilistic modeling and deep learning. Such systems enable the development of new probabilistic models and inference algorithms that would otherwise be impossible: enabling unprecedented scales to billions of parameters, distributed and mixed precision environments, and AI accelerators; integration with neural architectures for modeling massive and high-dimensional datasets; and the use of computation graphs for automatic differentiation and arbitrary manipulation of probabilistic programs for flexible inference and model criticism.

After describing deep probabilistic programming, we discuss applications in novel variational inference algorithms and deep probabilistic models. First, we introduce the variational Gaussian process (VGP), a Bayesian nonparametric variational family, which adapts its shape to match complex posterior distributions. The VGP generates approximate posterior samples by generating latent inputs and warping them through random non-linear mappings; the distribution over random mappings is learned during inference, enabling the transformed outputs to adapt to varying complexity of the true posterior. Second, we introduce hierarchical implicit models (HIMs). HIMs combine the idea of implicit densities with hierarchical Bayesian modeling, thereby defining models via simulators of data with rich hidden structure.


  • thumnail for Tran_columbia_0054D_16205.pdf Tran_columbia_0054D_16205.pdf application/pdf 1 MB Download File

More About This Work

Academic Units
Computer Science
Thesis Advisors
Blei, David Meir
Ph.D., Columbia University
Published Here
September 21, 2020