Nonparametric Density Estimation under Besov IPM Losses

02/09/2019
by   Ananya Uppal, et al.
0

We study the problem of estimating a nonparametric probability distribution under a family of losses called Besov IPMs. This family is quite large, including, for example, L^p distances, total variation distance, and generalizations of both Wasserstein (earthmover's) and Kolmogorov-Smirnov distances. For a wide variety of settings, we provide both lower and upper bounds, identifying precisely how the choice of loss function and assumptions on the data distribution interact to determine the mini-max optimal convergence rate. We also show that, in many cases, linear distribution estimates, such as the empirical distribution or kernel density estimator, cannot converge at the optimal rate. These bounds generalize, unify, or improve on several recent and classical results. Moreover, IPMs can be used to formalize a statistical model of generative adversarial networks (GANs). Thus, we show how our results imply bounds on the statistical error of a GAN, showing, for example, that, in many cases, GANs can strictly outperform the best linear estimator.

READ FULL TEXT
research
04/18/2020

Robust Density Estimation under Besov IPM Losses

We study minimax convergence rates of nonparametric density estimation i...
research
05/22/2018

Nonparametric Density Estimation under Adversarial Losses

We study minimax convergence rates of nonparametric density estimation u...
research
11/07/2018

On How Well Generative Adversarial Networks Learn Densities: Nonparametric and Parametric Results

We study in this paper the rate of convergence for learning distribution...
research
02/15/2021

Reconstructing measures on manifolds: an optimal transport approach

Assume that we observe i.i.d. points lying close to some unknown d-dimen...
research
12/21/2017

How Well Can Generative Adversarial Networks (GAN) Learn Densities: A Nonparametric View

We study in this paper the rate of convergence for learning densities un...
research
02/02/2022

Robust Estimation for Nonparametric Families via Generative Adversarial Networks

We provide a general framework for designing Generative Adversarial Netw...
research
03/27/2020

Tests and estimation strategies associated to some loss functions

We consider the problem of estimating the joint distribution of n indepe...

Please sign up or login with your details

Forgot password? Click here to reset