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

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models — mentioned by duvenaud

Fri, 14 Dec 2018 17:53:53 GMT

1. As the other reply said, we just mean an ODE solver whose internal operations are a detail we don't need to worry about. 2. This paper only had proofs of concepts and toy demos. But our follow-up paper, FFJORD [https://arxiv.org/abs/1810.01367] we used the continuous normalizing flows to get SOTA efficiently sample-able density models.

Paper and discussion history. A mention is not an endorsement.

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models — mentioned by duvenaud

Fri, 14 Dec 2018 04:00:43 GMT

Good question. The model developed in that paper, (neural autoregressive flows) is a discrete-layered architecture. It's a member of the Normalizing Flows family of models. Normalizing flows define a parametric density by transforming a sample from a Gaussian by a series of transformations: z0 ~ Normal(0, I) z1 = f1(z0) z2 = f2(z1) z3 = f3(z2) x = f4(z3) and they use the change of variables formula to compute p(x): log p(x) = log p(z0) + log det | df/dz0 | In our paper, we propose a continuous-time version of normalizing flows, called Continuous Normalizing Flows. We derived a continuous-time…

Paper and discussion history. A mention is not an endorsement.

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models — mentioned by duvenaud

Fri, 14 Dec 2018 01:02:32 GMT

Senior author here, I'm happy to answer any questions. We just released source code: https://github.com/rtqichen/torchdiffeq . This includes PyTorch implementations of adaptive ODE solvers that can be differentiated through automatically. So you can mix and match these ODE solvers with any other differentiable model component. There's already been a bit of follow-up work, turning Continuous Normalizing Flows into a practical generative density model: https://arxiv.org/abs/1810.01367 And now we're mainly working on 1) Regularizing ODE nets to be faster to solve and 2) getting the time-series…

Paper and discussion history. A mention is not an endorsement.