Robust Density Estimation under Besov IPM Losses

Abstract

We study minimax convergence rates of nonparametric density estimation in the Huber contamination model, in which a proportion of the data comes from an unknown outlier distribution. We provide the first results for this problem under a large family of losses, called Besov integral probability metrics (IPMs), that includes ${\mathcal{L}}^p$, Wasserstein, Kolmogorov-Smirnov, and other common distances between probability distributions. Specifically, under a range of smoothness assumptions on the population and outlier distributions, we show that a re-scaled thresholding wavelet series estimator achieves minimax optimal convergence rates under a wide variety of losses. Finally, based on connections that have recently been shown between nonparametric density estimation under IPM losses and generative adversarial networks (GANs), we show that certain GAN architectures also achieve these minimax rates.

References in corpus (6)

• Learning in Implicit Generative Models
• Amortised MAP Inference for Image Super-resolution
• Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
• Nonparametric Density Estimation under Adversarial Losses
• How Well Generative Adversarial Networks Learn Distributions
• MONK -- Outlier-Robust Mean Embedding Estimation by Median-of-Means