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

03/05/2019
by   Chao Gao, et al.
0

Robust scatter estimation is a fundamental task in statistics. The recent discovery on the connection between robust estimation and generative adversarial nets (GANs) by Gao et al. (2018) suggests that it is possible to compute depth-like robust estimators using similar techniques that optimize GANs. In this paper, we introduce a general learning via classification framework based on the notion of proper scoring rules. This framework allows us to understand both matrix depth function and various GANs through the lens of variational approximations of f-divergences induced by proper scoring rules. We then propose a new class of robust scatter estimators in this framework by carefully constructing discriminators with appropriate neural network structures. These estimators are proved to achieve the minimax rate of scatter estimation under Huber's contamination model. Our numerical results demonstrate its good performance under various settings against competitors in the literature.

READ FULL TEXT
research
10/04/2018

Robust Estimation and Generative Adversarial Nets

Robust estimation under Huber's ϵ-contamination model has become an impo...
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
06/19/2018

Properization: Constructing Proper Scoring Rules via Bayes Acts

Scoring rules serve to quantify predictive performance. A scoring rule i...
research
09/01/2020

A Mathematical Introduction to Generative Adversarial Nets (GAN)

Generative Adversarial Nets (GAN) have received considerable attention s...
research
02/02/2022

Robust Estimation for Nonparametric Families via Generative Adversarial Networks

We provide a general framework for designing Generative Adversarial Netw...
research
12/15/2021

Probabilistic Forecasting with Conditional Generative Networks via Scoring Rule Minimization

Probabilistic forecasting consists of stating a probability distribution...
research
12/24/2021

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

Consider the problem of simultaneous estimation of location and variance...

Please sign up or login with your details

Forgot password? Click here to reset