Isolating Sources of Disentanglement in Variational Autoencoders

Oct 22, 2018

Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

Oct 22, 2018

Ricky T. Q. Chen, Xuechen Li, Roger Grosse, David Duvenaud

* Added more experiments and improved clarity

**Click to Read Paper**

Neural Ordinary Differential Equations

Oct 22, 2018

Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud

Oct 22, 2018

Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud

**Click to Read Paper**

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models

Oct 22, 2018

Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud

A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be used if the transformation is specified by an ordinary differential equation. In this paper, we use Hutchinson's trace estimator to give a scalable unbiased estimate of the log-density. The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures. We demonstrate our approach on high-dimensional density estimation, image generation, and variational inference, achieving the state-of-the-art among exact likelihood methods with efficient sampling.
Oct 22, 2018

Will Grathwohl, Ricky T. Q. Chen, Jesse Bettencourt, Ilya Sutskever, David Duvenaud

* 8 Pages, 6 figures

**Click to Read Paper**