A Hilbert Space Embedding for Distributions

DOI10.1007/978-3-540-75225-7_5zbMath1142.68407OpenAlexW1946137962MaRDI QIDQ3520045

Arthur Gretton, Le Song, Bernhard Schölkopf, Alexander J. Smola

Publication date: 19 August 2008

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-540-75225-7_5

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

State-based confidence bounds for data-driven stochastic reachability using Hilbert space embeddings, A Rigorous Theory of Conditional Mean Embeddings, Bayesian Kernel Two-Sample Testing, Strictly Positive-Definite Spike Train Kernels for Point-Process Divergences, Frameworks and results in distributionally robust optimization, Distribution regression model with a Reproducing Kernel Hilbert Space approach, An efficient spread-based evolutionary algorithm for solving dynamic multi-objective optimization problems, Two-sample test for equal distributions in separate metric space: New maximum mean discrepancy based approaches, Bayesian object matching, Compressive statistical learning with random feature moments, Large-scale eigenvector approximation via Hilbert space embedding Nyström, Born machine model based on matrix product state quantum circuit, A test of independence based on a generalized correlation function, A Riemann-Stein kernel method, Expected similarity estimation for large-scale batch and streaming anomaly detection, Matching samples of multiple views, Nonasymptotic one- and two-sample tests in high dimension with unknown covariance structure, SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods, Unnamed Item, Stein's method meets computational statistics: a review of some recent developments, On harmonic Hilbert spaces on compact abelian groups, An introduction to kernel and operator learning methods for homogenization by self-consistent clustering analysis, A geometric view on the role of nonlinear feature maps in few-shot learning, High-order sequential simulation via statistical learning in reproducing kernel Hilbert space, Coefficient-based regularized distribution regression, Hilbert C∗-Module for Analyzing Structured Data, From statistical to causal learning, Sharp Analysis of Sketch-and-Project Methods via a Connection to Randomized Singular Value Decomposition, Large-scale kernel methods for independence testing, Multivariate tests of independence based on a new class of measures of independence in reproducing kernel Hilbert space, On minimum distribution discrepancy support vector machine for domain adaptation, Unnamed Item, Expected Conditional Characteristic Function-based Measures for Testing Independence, FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test, Filtering with State-Observation Examples via Kernel Monte Carlo Filter, Singular Value Decomposition of Operators on Reproducing Kernel Hilbert Spaces, Model-free inference of diffusion networks using RKHS embeddings, Testing independence of functional variables by angle covariance, A parameter estimation method using linear response statistics: Numerical scheme, Unsupervised group matching with application to cross-lingual topic matching without alignment information, Kernel embedding based variational approach for low-dimensional approximation of dynamical systems, Remember the curse of dimensionality: the case of goodness-of-fit testing in arbitrary dimension, A Kernel Embedding–Based Approach for Nonstationary Causal Model Inference, Unnamed Item, The Signature Kernel Is the Solution of a Goursat PDE, Kernel method for persistence diagrams via kernel embedding and weight factor, Characteristic and Universal Tensor Product Kernels, A class of optimal estimators for the covariance operator in reproducing kernel Hilbert spaces, The kernel Kalman rule. Efficient nonparametric inference by recursive least-squares and subspace projections, Equivalence of distance-based and RKHS-based statistics in hypothesis testing, Dimensionality reduction of complex metastable systems via kernel embeddings of transition manifolds, Assessment of ordered sequential data assimilation, Probability error bounds for approximation of functions in reproducing kernel Hilbert spaces, A theoretical and empirical analysis of support vector machine methods for multiple-instance classification, Computing functions of random variables via reproducing kernel Hilbert space representations, Symmetry exploits for Bayesian cubature methods, On the positivity and magnitudes of Bayesian quadrature weights, Eigendecompositions of transfer operators in reproducing kernel Hilbert spaces, Global sensitivity analysis with dependence measures, Discussion of: Brownian distance covariance, Global Sensitivity Analysis for Optimization with Variable Selection, Admissible kernels for RKHS embedding of probability distributions, Training image free high-order stochastic simulation based on aggregated kernel statistics, Kernel-Based Tests for Joint Independence, Minimax Estimation of Kernel Mean Embeddings, On the analysis of adaptability in multi-source domain adaptation, A deep learning framework for hybrid heterogeneous transfer learning, Probabilistic integration: a role in statistical computation?, Model-based kernel sum rule: kernel Bayesian inference with probabilistic models, Unnamed Item, Unnamed Item, A Generalized Kernel Method for Global Sensitivity Analysis, Mean-Field Controls with Q-Learning for Cooperative MARL: Convergence and Complexity Analysis, High-dimensional variable screening through kernel-based conditional mean dependence, Similarity, kernels, and the fundamental constraints on cognition

Uses Software

Kernel-Machines

Cites Work