Maximum effective dimension and information gain
David Janz, Arya Akhavan, Alexandre B. Tsybakov
Abstract
We establish general upper bounds on the maximum effective dimension and information gain of kernel Gram matrices over arbitrary designs in terms of approximation properties of the kernel or, equivalently, of the corresponding reproducing kernel Hilbert space. We show that across three regularity regimes, covering as special cases the Matérn and squared exponential kernels, these bounds cannot be improved beyond constant factors.
Create a lesson
Related papers
Minimax optimality for sequential gradient-free minimization of smooth functions and their derivatives
Théo Paquier, Alexandre B Tsybakov, François Portier et al.
Randomization Inference with Concentration Inequalities
Tobias Freidling
On the continuity of the Tukey depth function for fuzzy data
Luis González-De La Fuente, Alicia Nieto-Reyes, Pedro Terán
Recursive-Head Geometry and Order-Free Efficient Inference in Finite-State Nested Markov Models
Haoyu Wei
Finite-Sample Hausdorff Bounds and Hadamard Sensitivity for Regressions with MNAR Covariates
Hugo Dunias
Semiparametric Efficient Inference under Non-Informative Complex Survey Designs
Hiroki Chiba, Kosuke Morikawa