On optimal recovery in L_2

10/07/2020
by   V. Temlyakov, et al.
0

We prove that the optimal error of recovery in the L_2 norm of functions from a class can be bounded above by the value of the Kolmogorov width of in the uniform norm. We demonstrate on a number of examples of from classes of functions with mixed smoothness that the obtained inequality provides a powerful tool for estimating errors of optimal recovery.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/17/2020

Bounds on Kolmogorov widths and sampling recovery for classes with small mixed smoothness

Results on asymptotic characteristics of classes of functions with mixed...
research
01/14/2023

Universal discretization and sparse sampling recovery

Recently, it was discovered that for a given function class 𝐅 the error ...
research
04/27/2023

Tractability of sampling recovery on unweighted function classes

It is well-known that the problem of sampling recovery in the L_2-norm o...
research
02/25/2021

Recovery of regular ridge functions on the ball

We consider the problem of the uniform (in L_∞) recovery of ridge functi...
research
04/01/2020

Instances of Computational Optimal Recovery: Refined Approximability Models

Models based on approximation capabilities have recently been studied in...
research
09/12/2022

Full Recovery from Point Values: an Optimal Algorithm for Chebyshev Approximability Prior

Given pointwise samples of an unknown function belonging to a certain mo...
research
09/24/2020

L_2-norm sampling discretization and recovery of functions from RKHS with finite trace

We provide a spectral norm concentration inequality for infinite random ...

Please sign up or login with your details

Forgot password? Click here to reset