paper-with-me

Papers

Flows for simultaneous manifold learning and density estimation

2020-03-31 · NeurIPS 2020 12 · Johann Brehmer, Kyle Cranmer

We introduce manifold-learning flows (M-flows), a new class of generative models that simultaneously learn the data manifold as well as a tractable probability density on that manifold. Combining aspects of normalizing flows, GANs, autoencoders, and energy-based models, they have the potential to represent datasets with a manifold structure more faithfully and provide handles on dimensionality reduction, denoising, and out-of-distribution detection. We argue why such models should not be trained by maximum likelihood alone and present a new training algorithm that separates manifold and density updates. In a range of experiments we demonstrate how M-flows learn the data manifold and allow for better inference than standard flows in the ambient data space.

📄 PDF Abstract BibTeX arXiv:2003.13913

Code (2)

johannbrehmer/manifold-flow 공식 구현 pytorch
layer6ai-labs/rectangular-flows pytorch

Tasks

DenoisingDensity EstimationDimensionality ReductionOut-of-Distribution Detection

Similar Papers 제목 키워드 기반

Joint Manifold Learning and Density Estimation Using Normalizing Flows

2022-06-07 · Seyedeh Fatemeh Razavi, Mohammad Mahdi Mehmanchi, Reshad Hosseini, Mostafa Tavassolipour

Based on the manifold hypothesis, real-world data often lie on a low-dimensional manifold, while normalizing flows as a likelihood-based generative model are incapable of finding this manifold due to their structural con…

Density Estimation

Conformal Embedding Flows: Tractable Density Estimation on Learned Manifolds

2021-06-02 · ICML Workshop INNF 2021 7 · Brendan Leigh Ross, Jesse C Cresswell

Normalizing flows are generative models that provide tractable density estimation by transforming a simple distribution into a complex one. However, flows cannot directly model data supported on an unknown low-dimensiona…

Density Estimation

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

2021-06-09 · NeurIPS 2021 12 · Brendan Leigh Ross, Jesse C. Cresswell

Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution. However, this technique cannot directly…

Density Estimation

Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows

2021-12-01 · NeurIPS 2021 12 · Brendan Ross, Jesse Cresswell

Normalizing flows are generative models that provide tractable density estimation via an invertible transformation from a simple base distribution to a complex target distribution. However, this technique cannot directly…

Density Estimation

Normalizing Flows on Riemannian Manifolds

2016-11-07 · Mevlana C. Gemici, Danilo Rezende, Shakir Mohamed

We consider the problem of density estimation on Riemannian manifolds. Density estimation on manifolds has many applications in fluid-mechanics, optics and plasma physics and it appears often when dealing with angular va…

Density EstimationProtein Folding