Universal algorithms for learning theory. I: Piecewise constant functions.
From MaRDI portal
Recommendations
Cited in
(42)- Universal discretization
- Smooth fixed volume discrepancy, dispersion, and related problems
- Data-driven discovery of emergent behaviors in collective dynamics
- Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories
- Multiscale regression on unknown manifolds
- Connections between numerical integration, discrepancy, dispersion, and universal discretization
- Exact asymptotic orders of various randomized widths on Besov classes
- Approximation of functions over manifolds: a moving least-squares approach
- On universal estimators in learning theory
- A class of Laplacian multiwavelets bases for high-dimensional data
- Optimal shift invariant spaces and their Parseval frame generators
- Learning with sample dependent hypothesis spaces
- Universal algorithms for learning theory. II: Piecewise polynomial functions
- Distribution-free learning theory for approximating submanifolds from reptile motion capture data
- Conditional regression for single-index models
- Bayesian manifold regression
- Inferring interaction rules from observations of evolutive systems I: The variational approach
- Note on universal algorithms for learning theory
- A universal model based on minimax average divergence
- Analysis of discrete L^2 projection on polynomial spaces with random evaluations
- Multi-scale geometric methods for data sets. II: Geometric multi-resolution analysis
- scientific article; zbMATH DE number 1104348 (Why is no real title available?)
- Learning by canonical smooth estimation. II. Learning and choice of model complexity
- Error Estimates for Multivariate Regression on Discretized Function Spaces
- Learning interaction kernels in heterogeneous systems of agents from multiple trajectories
- Histogram transform ensembles for large-scale regression
- Constructing least-squares polynomial approximations
- Adaptive geometric multiscale approximations for intrinsically low-dimensional data
- Universality in approximation and estimation
- Universal piecewise polynomial estimators for machine learning
- Learning theory for inferring interaction kernels in second-order interacting agent systems
- Universal regression with adversarial responses
- On universal sampling recovery in the uniform norm
- On the iterative regularization of non-linear illposed problems in \(L^{\infty}\)
- Do stable neural networks exist for classification problems? -- A new view on stability in AI
- Introduction: Wolfgang Dahmen's mathematical work (as of 2009)
- Deep neural networks are adaptive to function regularity and data distribution in approximation and estimation
- Expansive natural neural gradient flows for energy minimization
- Construction and Monte Carlo estimation of wavelet frames generated by a reproducing kernel
- Nonlinear projection recovery in digital inpainting for color image restoration
- Convergence estimates in probability and in expectation for discrete least squares with noisy evaluations at random points
- Risk bounds for random regression graphs
This page was built for publication: Universal algorithms for learning theory. I: Piecewise constant functions.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3546378)
