Riemannian Continuous Normalizing Flows
- URL: http://arxiv.org/abs/2006.10605v2
- Date: Wed, 9 Dec 2020 14:01:13 GMT
- Title: Riemannian Continuous Normalizing Flows
- Authors: Emile Mathieu and Maximilian Nickel
- Abstract summary: We introduce continuous normalizing flows, a model which defines flows as the solution to ordinary differential equations.
We show that this approach can lead to substantial improvements on both synthetic and real-world data.
- Score: 21.879366166261228
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Normalizing flows have shown great promise for modelling flexible probability
distributions in a computationally tractable way. However, whilst data is often
naturally described on Riemannian manifolds such as spheres, torii, and
hyperbolic spaces, most normalizing flows implicitly assume a flat geometry,
making them either misspecified or ill-suited in these situations. To overcome
this problem, we introduce Riemannian continuous normalizing flows, a model
which admits the parametrization of flexible probability measures on smooth
manifolds by defining flows as the solution to ordinary differential equations.
We show that this approach can lead to substantial improvements on both
synthetic and real-world data when compared to standard flows or previously
introduced projected flows.
Related papers
- Conformal inference for regression on Riemannian Manifolds [49.7719149179179]
We investigate prediction sets for regression scenarios when the response variable, denoted by $Y$, resides in a manifold, and the covariable, denoted by X, lies in Euclidean space.
We prove the almost sure convergence of the empirical version of these regions on the manifold to their population counterparts.
arXiv Detail & Related papers (2023-10-12T10:56:25Z) - Flows for Flows: Training Normalizing Flows Between Arbitrary
Distributions with Maximum Likelihood Estimation [0.0]
Normalizing flows are constructed from a base distribution with a known density and a diffeomorphism with a tractable Jacobian.
The base density of a normalizing flow can be parameterised by a different normalizing flow, thus allowing maps to be found between arbitrary distributions.
arXiv Detail & Related papers (2022-11-04T14:30:48Z) - ManiFlow: Implicitly Representing Manifolds with Normalizing Flows [145.9820993054072]
Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions.
We propose an optimization objective that recovers the most likely point on the manifold given a sample from the perturbed distribution.
Finally, we focus on 3D point clouds for which we utilize the explicit nature of NFs, i.e. surface normals extracted from the gradient of the log-likelihood and the log-likelihood itself.
arXiv Detail & Related papers (2022-08-18T16:07:59Z) - Riemannian Diffusion Schr\"odinger Bridge [56.20669989459281]
We introduce emphRiemannian Diffusion Schr"odinger Bridge to accelerate sampling of diffusion models.
We validate our proposed method on synthetic data and real Earth and climate data.
arXiv Detail & Related papers (2022-07-07T00:35:04Z) - Tractable Density Estimation on Learned Manifolds with Conformal
Embedding Flows [0.0]
Normalizing flows provide tractable density estimation by transforming a simple base distribution into a complex target distribution.
Recent attempts to remedy this have introduced geometric complications that defeat a central benefit of normalizing flows: exact density estimation.
We argue that composing a standard flow with a trainable conformal embedding is the most natural way to model manifold-supported data.
arXiv Detail & Related papers (2021-06-09T18:00:00Z) - Continuous normalizing flows on manifolds [0.342658286826597]
We describe how the recently introduced Neural ODEs and continuous normalizing flows can be extended to arbitrary smooth manifold.
We propose a general methodology for parameterizing vector fields on these spaces and demonstrate how gradient-based learning can be performed.
arXiv Detail & Related papers (2021-03-14T15:35:19Z) - Integrable Nonparametric Flows [5.9774834479750805]
We introduce a method for reconstructing an infinitesimal normalizing flow given only an infinitesimal change to a probability distribution.
This reverses the conventional task of normalizing flows.
We discuss potential applications to problems in quantum Monte Carlo and machine learning.
arXiv Detail & Related papers (2020-12-03T16:19:52Z) - SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows [78.77808270452974]
SurVAE Flows is a modular framework for composable transformations that encompasses VAEs and normalizing flows.
We show that several recently proposed methods, including dequantization and augmented normalizing flows, can be expressed as SurVAE Flows.
arXiv Detail & Related papers (2020-07-06T13:13:22Z) - Neural Manifold Ordinary Differential Equations [46.25832801867149]
We introduce Neural Manifold Ordinary Differential Equations, which enables the construction of Manifold Continuous Normalizing Flows (MCNFs)
MCNFs require only local geometry and compute probabilities with continuous change of variables.
We find that leveraging continuous manifold dynamics produces a marked improvement for both density estimation and downstream tasks.
arXiv Detail & Related papers (2020-06-18T03:24:58Z) - Stochastic Normalizing Flows [52.92110730286403]
We introduce normalizing flows for maximum likelihood estimation and variational inference (VI) using differential equations (SDEs)
Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs.
These SDEs can be used for constructing efficient chains to sample from the underlying distribution of a given dataset.
arXiv Detail & Related papers (2020-02-21T20:47:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.