Normalizing Flows Across Dimensions

06/23/2020
by   Edmond Cunningham, et al.
17

Real-world data with underlying structure, such as pictures of faces, are hypothesized to lie on a low-dimensional manifold. This manifold hypothesis has motivated state-of-the-art generative algorithms that learn low-dimensional data representations. Unfortunately, a popular generative model, normalizing flows, cannot take advantage of this. Normalizing flows are based on successive variable transformations that are, by design, incapable of learning lower-dimensional representations. In this paper we introduce noisy injective flows (NIF), a generalization of normalizing flows that can go across dimensions. NIF explicitly map the latent space to a learnable manifold in a high-dimensional data space using injective transformations. We further employ an additive noise model to account for deviations from the manifold and identify a stochastic inverse of the generative process. Empirically, we demonstrate that a simple application of our method to existing flow architectures can significantly improve sample quality and yield separable data embeddings.

READ FULL TEXT

page 2

page 6

page 7

page 16

page 17

page 18

page 19

page 20

06/18/2020

Variational Autoencoder with Learned Latent Structure

The manifold hypothesis states that high-dimensional data can be modeled...
06/07/2022

Joint Manifold Learning and Density Estimation Using Normalizing Flows

Based on the manifold hypothesis, real-world data often lie on a low-dim...
06/15/2020

Ordering Dimensions with Nested Dropout Normalizing Flows

The latent space of normalizing flows must be of the same dimensionality...
07/06/2022

The Union of Manifolds Hypothesis and its Implications for Deep Generative Modelling

Deep learning has had tremendous success at learning low-dimensional rep...
07/11/2022

Matching Normalizing Flows and Probability Paths on Manifolds

Continuous Normalizing Flows (CNFs) are a class of generative models tha...
03/02/2021

Learning disentangled representations via product manifold projection

We propose a novel approach to disentangle the generative factors of var...
10/25/2017

Relative Transfer Function Inverse Regression from Low Dimensional Manifold

In room acoustic environments, the Relative Transfer Functions (RTFs) ar...