ROBUST ESTIMATION VIA GENERATIVE ADVERSARIAL NETWORKS
Robust estimation under Huber's $\epsilon$-contamination model has become an important topic in statistics and theoretical computer science. Rate-optimal procedures such as Tukey's median and other estimators based on statistical depth functions are impractical because of their computational intractability. In this paper, we establish an intriguing connection between f-GANs and various depth functions through the lens of f-Learning. Similar to the derivation of f-GAN, we show that these depth functions that lead to rate-optimal robust estimators can all be viewed as variational lower bounds of the total variation distance in the framework of f-Learning. This connection opens the door of computing robust estimators using tools developed for training GANs. In particular, we show that a JS-GAN that uses a neural network discriminator with at least one hidden layer is able to achieve the minimax rate of robust mean estimation under Huber's $\epsilon$-contamination model. Interestingly, the hidden layers of the neural net structure in the discriminator class are shown to be necessary for robust estimation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Risk Management with Feature-Enriched Generative Adversarial Networks (FE-GAN)
This paper investigates the application of Feature-Enriched Generative Adversarial Networks (FE-GAN) in financial risk management, with a focus on improving the estimation of Value at Risk (VaR) and Expected Shortfall (E…
Generative Adversarial NetworkManagementGenerative Adversarial Nets from a Density Ratio Estimation Perspective
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger …
Density Ratio EstimationA Generative Adversarial Density Estimator
Density estimation is a challenging unsupervised learning problem. Current maximum likelihood approaches for density estimation are either restrictive or incapable of producing high-quality samples. On the other hand, li…
Density EstimationVisual DialogSGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks
Recently end-to-end unsupervised deep learning methods have achieved an effect beyond geometric methods for visual depth and ego-motion estimation tasks. These data-based learning methods perform more robustly and accura…
DecoderDepth EstimationGenerative Adversarial NetworkMotion Estimation+1GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments
Recent advancements have led to a proliferation of machine learning systems used to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations of these sy…
Objectobject-detectionObject DetectionPose Estimation+1