Tractable and Near-Optimal Adversarial Algorithms for Robust Estimation in Contaminated Gaussian Models

12/24/2021
by   Ziyue Wang, et al.
0

Consider the problem of simultaneous estimation of location and variance matrix under Huber's contaminated Gaussian model. First, we study minimum f-divergence estimation at the population level, corresponding to a generative adversarial method with a nonparametric discriminator and establish conditions on f-divergences which lead to robust estimation, similarly to robustness of minimum distance estimation. More importantly, we develop tractable adversarial algorithms with simple spline discriminators, which can be implemented via nested optimization such that the discriminator parameters can be fully updated by maximizing a concave objective function given the current generator. The proposed methods are shown to achieve minimax optimal rates or near-optimal rates depending on the f-divergence and the penalty used. We present simulation studies to demonstrate advantages of the proposed methods over classic robust estimators, pairwise methods, and a generative adversarial method with neural network discriminators.

READ FULL TEXT
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
01/20/2021

Robust W-GAN-Based Estimation Under Wasserstein Contamination

Robust estimation is an important problem in statistics which aims at pr...
research
10/04/2018

Robust Estimation and Generative Adversarial Nets

Robust estimation under Huber's ϵ-contamination model has become an impo...
research
11/02/2020

Complexity of near-optimal robust versions of multilevel optimization problems

Near-optimality robustness extends multilevel optimization with a limite...
research
07/13/2020

An Adversarial Approach to Structural Estimation

We propose a new simulation-based estimation method, adversarial estimat...
research
05/24/2017

Approximation and Convergence Properties of Generative Adversarial Learning

Generative adversarial networks (GAN) approximate a target data distribu...
research
03/05/2019

Generative Adversarial Nets for Robust Scatter Estimation: A Proper Scoring Rule Perspective

Robust scatter estimation is a fundamental task in statistics. The recen...

Please sign up or login with your details

Forgot password? Click here to reset