Diederik P. Kingma

An Introduction to Variational Autoencoders

Variational autoencoders provide a principled framework for learning deep\nlatent-variable models and corresponding inference models. In this work, we\nprovide an introduction t...

Fast Kd-Trees for the Kullback-Leibler Divergence and Other Decomposable Bregman Divergences

The contributions of the paper span theoretical and implementational results. First, we prove that Kd-trees can be extended to ℝ^d with the distance measured by an arbitrary Bre...

Designing complex, dynamic yet multi-functional materials and devices is challenging because the design spaces for these materials have numerous interdependent and often conflic...