On the optimal estimation of probability measures in weak and strong topologies

DOI10.3150/15-BEJ713zbMath1360.62163arXiv1310.8240MaRDI QIDQ282569

Bharath K. Sriperumbudur

Publication date: 12 May 2016

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1310.8240

zbMATH Keywords

exponential inequalitykernel density estimatoradaptive estimationreproducing kernel Hilbert spacetwo-sample testtotal variation distancebounded Lipschitz metricRademacher chaossmoothed empirical processesU-processesuniform central limit theorem

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Probability measures on topological spaces (60B05) Central limit and other weak theorems (60F05) Functional limit theorems; invariance principles (60F17)

Related Items (6)

Ivanov-Regularised Least-Squares Estimators over Large RKHSs and Their Interpolation Spaces ⋮ Directional differentiability for supremum-type functionals: statistical applications ⋮ Geometrical Insights for Implicit Generative Modeling ⋮ Unnamed Item ⋮ Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions ⋮ Minimax Estimation of Kernel Mean Embeddings

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
• Uniform limit theorems for wavelet density estimators
• Donsker-type theorems for nonparametric maximum likelihood estimators
• Uniform central limit theorems for kernel density estimators
• An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation
• Adaptation on the space of finite signed measures
• Empirical processes indexed by Lipschitz functions
• Optimal spatial adaptation to inhomogeneous smoothness: An approach based on kernel estimates with variable bandwidth selectors
• Wavelets, approximation, and statistical applications
• Nonparametric estimators which can be ``plugged-in.
• Weak convergence and empirical processes. With applications to statistics
• On the empirical estimation of integral probability metrics
• Local Rademacher complexities
• Hilbert space embeddings and metrics on probability measures
• Relationships between Donsker classes and Sobolev spaces
• Rademacher Chaos Complexities for Learning the Kernel Problem
• Support Vector Machines
• Uniform Central Limit Theorems
• Asymptotic Statistics
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Real Analysis and Probability
• Neural Network Learning
• Universality, Characteristic Kernels and RKHS Embedding of Measures
• Theory of Reproducing Kernels
• Scattered Data Approximation

This page was built for publication: On the optimal estimation of probability measures in weak and strong topologies