Optimal prediction of vector-valued functions from point samples

DOI10.1016/J.JCO.2025.101981MaRDI QIDQ6871315zbMATH OpenFDO

Authors Simon Foucart

Publication date 20 January 2026

Published in Journal of Complexity (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCO.2025.101981

zbMATH Keywords

predictionreproducing kernel Hilbert spacesminimax problemsoptimal recoverymoment-SOS hierarchydominated extension theorem

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Abstract approximation theory (approximation in normed linear spaces and other abstract spaces) (41A65) Algorithms for approximation of functions (65D15) Applications of functional analysis in numerical analysis (46N40)

Cites work

• scientific article; zbMATH DE number 4144656 (Why is no real title available?)
• scientific article; zbMATH DE number 936206 (Why is no real title available?)
• Computing a quantity of interest from observational data
• Determining projection constants of univariate polynomial spaces
• Full recovery from point values: an optimal algorithm for Chebyshev approximability prior
• Linear vs. nonlinear algorithms for linear problems
• Near-Optimal Estimation of Linear Functionals with Log-Concave Observation Errors
• Near-optimality of linear recovery from indirect observations
• Nonparametric estimation by convex programming
• On the existence of optimal affine methods for approximating linear functionals
• Projection Constants
• Radius of information for two intersected centered hyperellipsoids and implications in optimal recovery from inaccurate data
• Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory
• Statistical estimation and optimal recovery
• The moment-SOS hierarchy
• Understanding machine learning. From theory to algorithms

This page was built for publication: Optimal prediction of vector-valued functions from point samples

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6871315)