Abstract Support Vector (SV) Machines combine several techniques from statistics, machine learning and neural networks. One of the most important ingredients are kernels, ie the …
In this book some methods from the geometric theory of Banach spaces are used to prove asymptotic estimates for the eigenvalues of certain compact operators, in particular, of …
J Bourgain, A Pajor, SJ Szarek… - Geometric Aspects of …, 1989 - Springer
It is well known that an operator u acting between two Banach spaces X, Y is compact if and only if dual operator u· is compact. For any such u: Xt Y and for every e> 0, denote by N (u, e) …
We derive new bounds for the generalization error of kernel machines, such as support vector machines and related regularization networks by obtaining new bounds on their …
Given a finite-dimensional Banach space $ E $ and a Euclidean norm on $ E $, we study relations between the norm and the Euclidean norm on subspaces of $ E $ of small …
B Bowman, GF Montufar - Advances in Neural Information …, 2022 - proceedings.neurips.cc
We provide quantitative bounds measuring the $ L^ 2$ difference in function space between the trajectory of a finite-width network trained on finitely many samples from the idealized …
One of the most intensively disputed questions of computational mathematics is the following: What is the use of Monte Carlo methods, ie can it be of help to involve chance …
DD Haroske, L Skrzypczak - Revista matemática complutense, 2008 - eudml.org
We study compact embeddings for weighted spaces of Besov and Triebel hyphen Lizorkin type where the weight belongs to some Muckenhoupt A sub p class period.. For weights of …
For two convex bodies K and T in Rn, the covering number of K by T, denoted N (K, T), is defined as the minimal number of translates of T needed to cover K. Let us denote by the …