High-Dimensional Non-Parametric Density Estimation in Mixed Smooth Sobolev Spaces

Abstract

Density estimation plays a key role in many tasks in machine learning, statistical inference, and visualization. The main bottleneck in high-dimensional density estimation is the prohibitive computational cost and the slow convergence rate. In this paper, we propose novel estimators for high-dimensional non-parametric density estimation called the adaptive hyperbolic cross density estimators, which enjoys nice convergence properties in the mixed smooth Sobolev spaces. As modifications of the usual Sobolev spaces, the mixed smooth Sobolev spaces are more suitable for describing high-dimensional density functions in some applications. We prove that, unlike other existing approaches, the proposed estimator does not suffer the curse of dimensionality under Integral Probability Metric, including Hölder Integral Probability Metric, where Total Variation Metric and Wasserstein Distance are special cases. Applications of the proposed estimators to generative adversarial networks (GANs) and goodness of fit test for high-dimensional data are discussed to illustrate the proposed estimator's good performance in high-dimensional problems. Numerical experiments are conducted and illustrate the efficiency of our proposed method.

References in corpus (8)

• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality
• Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spaces
• Learning Deep Kernels for Non-Parametric Two-Sample Tests
• Approximation and Convergence Properties of Generative Adversarial Learning
• Minimax Distribution Estimation in Wasserstein Distance
• On the Optimality of Gaussian Kernel Based Nonparametric Tests against Smooth Alternatives
• On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests