Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
From MaRDI portal
Publication:5962345
DOI10.1007/s00365-009-9080-0zbMath1204.68157MaRDI QIDQ5962345
Publication date: 22 September 2010
Published in: Constructive Approximation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s00365-009-9080-0
eigenvalues; learning theory; reproducing kernel Hilbert spaces; Gaussian kernel; regularized least square algorithm
68T05: Learning and adaptive systems in artificial intelligence
68P30: Coding and information theory (compaction, compression, models of communication, encoding schemes, etc.) (aspects in computer science)
Related Items
Reproducing Properties of Differentiable Mercer-Like Kernels on the Sphere, Sparsity-promoting algorithms for the discovery of informative Koopman-invariant subspaces, Integration in reproducing kernel Hilbert spaces of Gaussian kernels, Unnamed Item, Learning Rates of lq Coefficient Regularization Learning with Gaussian Kernel, Learning Rates for Classification with Gaussian Kernels, Finite Sample Approximations of Exact and Entropic Wasserstein Distances Between Covariance Operators and Gaussian Processes, Determinantal Point Processes Implicitly Regularize Semiparametric Regression Problems, On a nonlinear extension of the principal fitted component model, Support vector machine adapted Tikhonov regularization method to solve Dirichlet problem, Linear and nonlinear approximation of spherical radial basis function networks, Learning rates of regularized regression on the unit sphere, Approximation of reachable sets using optimal control and support vector machines, Nonparametric regression using needlet kernels for spherical data, The regularized least squares algorithm and the problem of learning halfspaces, Worst-case optimal approximation with increasingly flat Gaussian kernels, Gaussian kernel quadrature at scaled Gauss-Hermite nodes, A least square point of view to reproducing kernel methods to solve functional equations, Interpolation and best approximation for spherical radial basis function networks, Kernel-based interpolation at approximate Fekete points, p-kernel Stein variational gradient descent for data assimilation and history matching, On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces, Learning from non-random data in Hilbert spaces: an optimal recovery perspective, Stochastic saddle-point optimization for the Wasserstein barycenter problem, On the mathematical foundations of stable RKHSs, On a collocation point of view to reproducing kernel methods, On the positivity and magnitudes of Bayesian quadrature weights, Kolmogorov widths on the sphere via eigenvalue estimates for Hölderian integral operators, Approximating and learning by Lipschitz kernel on the sphere, Nonlinear and additive principal component analysis for functional data, Small sample spaces for Gaussian processes, Low-rank kernel approximation of Lyapunov functions using neural networks, From Covariance Matrices to Covariance Operators: Data Representation from Finite to Infinite-Dimensional Settings
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Mercer theorem for RKHS on noncompact sets
- Model selection for regularized least-squares algorithm in learning theory
- Reproducing kernel Hilbert spaces associated with analytic translation-invariant Mercer kernels
- Generalization bounds for function approximation from scattered noisy data
- Optimal aggregation of classifiers in statistical learning.
- Approximation in learning theory
- Learning theory estimates via integral operators and their approximations
- On early stopping in gradient descent learning
- On the mathematical foundations of learning
- 10.1162/153244302760185252
- Theory of Classification: a Survey of Some Recent Advances
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
- An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
- Theory of Reproducing Kernels