This post demonstrates how to approximate the KL divergence (in fact, any f-divergence) between implicit distributions, using density ratio estimation by probabilistic classification.
We illustrate how to build complicated probability distributions in a modular fashion using the Bijector API from TensorFlow Probability.
A mobile visual clothing search system is presented whereby a smart phone user can either choose a social networking image or capture a new photo of a person wearing clothing of interest and search for similar clothing in a large cloud-based ecommerce database. The phone's GPS location is used to re-rank results by retail store location, to inform the user of local stores where similar clothing items can be tried on.
Expanding the scope and applicability of variational inference to encompass implicit probabilistic models.
Aboleth is a minimalistic TensorFlow framework for scalable Bayesian deep learning and Gaussian process approximation.
Determinant is a software service that makes predictions from sparse data, and learns what data it needs to optimise its performance.
Revrand is a full-featured Python library for Bayesian generalized linear models, with random basis kernels for large-scale Gaussian process approximations.
An in-depth practical guide to variational encoders from a probabilistic perspective.