Average Case Tractability of Non-homogeneous Tensor Product Problems
M. A. Lifshits, A. Papageorgiou, H. Wo\'zniakowski

TL;DR
This paper investigates the average case complexity of multivariate approximation problems with non-homogeneous tensor product structures, providing conditions for various tractability types based on eigenvalues of univariate kernels.
Contribution
It establishes necessary and sufficient conditions for different tractability notions in tensor product approximation problems using eigenvalue analysis.
Findings
Strong polynomial tractability occurs if liminf |ln g_k|/ln k > 1.
Conditions for polynomial and quasi-polynomial tractability are characterized.
Results are illustrated with Korobov kernel-based approximation problems.
Abstract
We study d-variate approximation problems in the average case setting with respect to a zero-mean Gaussian measure. Our interest is focused on measures having a structure of non-homogeneous linear tensor product, where covariance kernel is a product of univariate kernels. We consider the normalized average error of algorithms that use finitely many evaluations of arbitrary linear functionals. The information complexity is defined as the minimal number n(h,d) of such evaluations for error in the d-variate case to be at most h. The growth of n(h,d) as a function of h^{-1} and d depends on the eigenvalues of the covariance operator and determines whether a problem is tractable or not. Four types of tractability are studied and for each of them we find the necessary and sufficient conditions in terms of the eigenvalues of univariate kernels. We illustrate our results by considering…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMathematical Approximation and Integration · Advanced Numerical Analysis Techniques · Mathematical functions and polynomials
