Complexity of approximating Hölder classes from information with varying Gaussian noise

DOI10.1016/J.JCO.2020.101497zbMath1445.62012OpenAlexW3027576799MaRDI QIDQ2192676

Paweł M. Morkisz, Leszek Plaskota

Publication date: 17 August 2020

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

Full work available at URL: https://doi.org/10.1016/j.jco.2020.101497

zbMATH Keywords

Gaussian noiseinformationnumerical approximation\(\epsilon\)-complexityHölder functions

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Algorithms for approximation of functions (65D15) Statistical aspects of information-theoretic topics (62B10)

Related Items (4)

Worst case tractability of linear problems in the presence of noise: linear information ⋮ Euler scheme for approximation of solution of nonlinear ODEs under inexact information ⋮ Randomized Runge-Kutta method -- stability and convergence under inexact information ⋮ On the randomized Euler schemes for ODEs under inexact information

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimax risk over hyperrectangles, and implications
• Deterministic and stochastic error bounds in numerical analysis
• Asymptotic minimax risk for sup-norm loss: Solution via optimal recovery
• Average complexity for linear problems in a model with varying information noise
• Worst case complexity of problems with random information noise
• An Asymptotically Minimax Regression Estimator in the Uniform Norm up to Exact Constant
• Introduction to nonparametric estimation

This page was built for publication: Complexity of approximating Hölder classes from information with varying Gaussian noise