Intrinsic Multi-scale Evaluation of Generative Models

05/27/2019
by   Anton Tsitsulin, et al.
5

Generative models are often used to sample high-dimensional data points from a manifold with small intrinsic dimension. Existing techniques for comparing generative models focus on global data properties such as mean and covariance; in that sense, they are extrinsic and uni-scale. We develop the first, to our knowledge, intrinsic and multi-scale method for characterizing and comparing underlying data manifolds, based on comparing all data moments by lower-bounding the spectral notion of the Gromov-Wasserstein distance between manifolds. In a thorough experimental study, we demonstrate that our method effectively evaluates the quality of generative models; further, we showcase its efficacy in discerning the disentanglement process in neural networks.

READ FULL TEXT
11/21/2017

The Riemannian Geometry of Deep Generative Models

Deep generative models learn a mapping from a low dimensional latent spa...
07/01/2018

Heuristic Framework for Multi-Scale Testing of the Multi-Manifold Hypothesis

When analyzing empirical data, we often find that global linear models o...
06/08/2021

Manifold Topology Divergence: a Framework for Comparing Data Manifolds

We develop a framework for comparing data manifolds, aimed, in particula...
06/28/2018

Learning Implicit Generative Models with the Method of Learned Moments

We propose a method of moments (MoM) algorithm for training large-scale ...
05/14/2019

Learning Generative Models across Incomparable Spaces

Generative Adversarial Networks have shown remarkable success in learnin...
06/27/2019

Curriculum Learning for Deep Generative Models with Clustering

Training generative models like generative adversarial networks (GANs) a...
02/09/2021

Generative Models as Distributions of Functions

Generative models are typically trained on grid-like data such as images...

Code Repositories

imd

Code for MSID, a Multi-Scale Intrinsic Distance for comparing generative models, studying neural networks, and more!


view repo