Statistical and Topological Properties of Sliced Probability Divergences

by   Kimia Nadjahi, et al.

The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence' between one-dimensional random projections of the two measures. However, the computational and statistical consequences of such a technique have not yet been well-established. In this paper, we aim at bridging this gap and derive some properties of sliced divergence functions. First, we show that slicing preserves the metric axioms and the weak continuity of the divergence, implying that the sliced divergence will share similar topological properties. We then precise the results in the case where the base divergence belongs to the class of integral probability metrics. On the other hand, we establish that, under mild conditions, the sample complexity of the sliced divergence does not depend on the dimension, even when the base divergence suffers from the curse of dimensionality. We finally apply our general results to the Wasserstein distance and Sinkhorn divergences, and illustrate our theory on both synthetic and real data experiments.


page 1

page 2

page 3

page 4


Divergence measures estimation and its asymptotic normality theory : Discrete case

In this paper we provide the asymptotic theory of the general phi-diverg...

The Cramer Distance as a Solution to Biased Wasserstein Gradients

The Wasserstein probability metric has received much attention from the ...

Scaling of Model Approximation Errors and Expected Entropy Distances

We compute the expected value of the Kullback-Leibler divergence to vari...

Statistical Detection of Collective Data Fraud

Statistical divergence is widely applied in multimedia processing, basic...

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Level, and Frontier Integral

The spectacular success of deep generative models calls for quantitative...

Estimating 2-Sinkhorn Divergence between Gaussian Processes from Finite-Dimensional Marginals

Optimal Transport (OT) has emerged as an important computational tool in...

Relaxed Wasserstein with Applications to GANs

We propose a novel class of statistical divergences called Relaxed Wasse...

Please sign up or login with your details

Forgot password? Click here to reset