Universality, Characteristic Kernels and RKHS Embedding of Measures

zbMath1280.68198arXiv1003.0887MaRDI QIDQ5396683

Gert R. G. Lanckriet, Kenji Fukumizu, Bharath K. Sriperumbudur

Publication date: 3 February 2014

Full work available at URL: https://arxiv.org/abs/1003.0887

kernel methods binary classification homogeneity testing radial kernels translation invariant kernels universal kernels strictly positive definite kernels Hilbert space embeddings characteristic kernels conditionally strictly positive definite kernels integrally strictly positive definite kernels

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (61)

Supermix: sparse regularization for mixtures ⋮ State-based confidence bounds for data-driven stochastic reachability using Hilbert space embeddings ⋮ Kernel partial correlation: a novel approach to capturing conditional independence in graphical models for noisy data ⋮ On length measures of planar closed curves and the comparison of convex shapes ⋮ A Rigorous Theory of Conditional Mean Embeddings ⋮ Operator-theoretic framework for forecasting nonlinear time series with kernel analog techniques ⋮ On the optimal estimation of probability measures in weak and strong topologies ⋮ On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces ⋮ Generalized Optimal Matching Methods for Causal Inference ⋮ Nonparametric stochastic approximation with large step-sizes ⋮ A preconditioning technique for Krylov subspace methods in RKHSs ⋮ The fshape framework for the variability analysis of functional shapes ⋮ Distribution regression model with a Reproducing Kernel Hilbert Space approach ⋮ Strictly proper kernel scores and characteristic kernels on compact spaces ⋮ Operator-valued positive definite kernels and differentiable universality ⋮ Universally consistent vertex classification for latent positions graphs ⋮ The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach ⋮ Sparse regularized learning in the reproducing kernel Banach spaces with the \(\ell^1\) norm ⋮ A Riemann-Stein kernel method ⋮ Fairness improvement for black-box classifiers with Gaussian process ⋮ Sparse machine learning in Banach spaces ⋮ Unnamed Item ⋮ Weighted signature kernels ⋮ Quantum Mechanics for Closure of Dynamical Systems ⋮ Nonlinear directed acyclic graph estimation based on the kernel partial correlation coefficient ⋮ A New and Unified Family of Covariate Adaptive Randomization Procedures and Their Properties ⋮ A duality approach to regularized learning problems in Banach spaces ⋮ On harmonic Hilbert spaces on compact abelian groups ⋮ Geometrical Insights for Implicit Generative Modeling ⋮ A Kernel Log-Rank Test of Independence for Right-Censored Data ⋮ Hilbert C∗-Module for Analyzing Structured Data ⋮ OptimalA PrioriBalance in the Design of Controlled Experiments ⋮ Unnamed Item ⋮ Comparing a large number of multivariate distributions ⋮ FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test ⋮ Some Properties of Reproducing Kernel Banach and Hilbert Spaces ⋮ Krylov subspace methods for estimating operator-vector multiplications in Hilbert spaces ⋮ Kernel embedding based variational approach for low-dimensional approximation of dynamical systems ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions ⋮ Kernel method for persistence diagrams via kernel embedding and weight factor ⋮ Statistical inference on random dot product graphs: a survey ⋮ Characteristic and Universal Tensor Product Kernels ⋮ A Kernel Multiple Change-point Algorithm via Model Selection ⋮ Equivalence of distance-based and RKHS-based statistics in hypothesis testing ⋮ Continuum versus discrete networks, graph Laplacians, and reproducing kernel Hilbert spaces ⋮ Scalable high-resolution forecasting of sparse spatiotemporal events with kernel methods: a winning solution to the NIJ ``Real-time crime forecasting challenge ⋮ Learning sparse conditional distribution: an efficient kernel-based approach ⋮ Metrics, quantization and registration in varifold spaces ⋮ Generalized support vector regression: Duality and tensor-kernel representation ⋮ Admissible kernels for RKHS embedding of probability distributions ⋮ Quantum dynamics of the classical harmonic oscillator ⋮ On extension theorems and their connection to universal consistency in machine learning ⋮ Minimax Estimation of Kernel Mean Embeddings ⋮ Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions ⋮ Unnamed Item ⋮ Antithetic and Monte Carlo kernel estimators for partial rankings ⋮ A Generalized Kernel Method for Global Sensitivity Analysis ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs

This page was built for publication: Universality, Characteristic Kernels and RKHS Embedding of Measures