English
Related papers

Related papers: Towards Empirical Process Theory for Vector-Valued…

200 papers

Identifying meaningful signal buried in noise is a problem of interest arising in diverse scenarios of data-driven modeling. We present here a theoretical framework for exploiting intrinsic geometry in data that resists noise corruption,…

Machine Learning · Statistics 2018-01-26 Ishanu Chattopadhyay

The purpose of this article is to develop a technique to estimate certain bounds for entropy numbers of diagonal operator on spaces of p-summable sequences for finite p greater than 1. The approximation method we develop in this direction…

Functional Analysis · Mathematics 2022-07-08 K. P. Deepesh , V. B. Kiran Kumar

We study in this paper real-valued functions on the space of all sub-$\sigma$-algebras of a probability measure space, and introduce the notion of Kudo-continuity, which is an a priori strengthening of continuity with respect to strong…

Probability · Mathematics 2020-02-18 Michael Björklund , Yair Hartman , Hanna Oppelmayer

We consider a randomly forced Ginzburg-Landau equation on an unbounded domain. The forcing is smooth and homogeneous in space and white noise in time. We prove existence and smoothness of solutions, existence of an invariant measure for the…

Analysis of PDEs · Mathematics 2007-05-23 Jacques Rougemont

In this paper we study some aspects of thermodynamic formalism, more specifically topological pressure and, as a consequence, topological entropy for piecewise smooth vector fields, using topological conjugation with shift maps and the…

Dynamical Systems · Mathematics 2022-11-09 Marco A. C. Florentino , Tiago Carvalho , Jeferson Cassiano

Functional data that are nonnegative and have a constrained integral can be considered as samples of one-dimensional density functions. Such data are ubiquitous. Due to the inherent constraints, densities do not live in a vector space and,…

Statistics Theory · Mathematics 2016-01-13 Alexander Petersen , Hans-Georg Müller

Understanding and certifying the generalization performance of machine learning algorithms -- i.e. obtaining theoretical estimates of the test error from the training error -- is a central theme of statistical learning theory. Among the…

Machine Learning · Computer Science 2026-05-26 Sho Sonoda , Kazumi Kasaura , Yuma Mizuno , Kei Tsukamoto , Naoto Onda

This article discusses the notion of convergence of sequences of iterated function systems. The technique of iterated function systems is one of the several methods to construct objects with fractal nature, and the fractals obtained with…

Dynamical Systems · Mathematics 2022-12-09 Praveen M , Sunil Mathew

Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces remains unexplored.…

Machine Learning · Computer Science 2025-09-15 Jianxin Zhang , Clayton Scott

We develop a version of Herbrand's theorem for continuous logic and use it to prove that definable functions in infinite-dimensional Hilbert spaces are piecewise approximable by affine functions. We obtain similar results for definable…

Logic · Mathematics 2011-07-20 Isaac Goldbring

We show the flexibility of the metric entropy and obtain additional restrictions on the topological entropy of geodesic flow on closed surfaces of negative Euler characteristic with smooth non-positively curved Riemannian metrics with fixed…

Dynamical Systems · Mathematics 2020-08-07 Thomas Barthelmé , Alena Erchenko

In this paper, we present a maximum likelihood estimation approach to determine the value vector in transformer models. We model the sequence of value vectors, key vectors, and the query vector as a sequence of Gaussian distributions. The…

Machine Learning · Computer Science 2025-09-17 Jiyong Ma

In this paper, we obtain some uniform laws of large numbers and functional central limit theorems for sequential empirical measure processes indexed by classes of product functions satisfying appropriate Vapnik-Chervonenkis properties.

Probability · Mathematics 2008-11-03 Omar El-Dakkak

We study multivariate integration and approximation for functions belonging to a weighted reproducing kernel Hilbert space based on half-period cosine functions in the worst-case setting. The weights in the norm of the function space depend…

Numerical Analysis · Mathematics 2015-11-23 Christian Irrgeher , Peter Kritzer , Friedrich Pillichshammer

The Gromoll-Meyer's generalized Morse lemma (so called splitting lemma) near degenerate critical points on Hilbert spaces, which is one of key results in infinite dimensional Morse theory, is usually stated for at least $C^2$-smooth…

Functional Analysis · Mathematics 2014-06-12 Guangcun Lu

For a finite function class we describe the large sample limit of the sequential Rademacher complexity in terms of the viscosity solution of a $G$-heat equation. In the language of Peng's sublinear expectation theory, the same quantity…

Machine Learning · Computer Science 2016-05-13 Dmitry B. Rokhlin

We derive an upper bound for the mean of the supremum of the empirical process indexed by a class of functions that are known to have variance bounded by a small constant $\delta$. The bound is expressed in the uniform entropy integral of…

Statistics Theory · Mathematics 2010-12-30 Aad van der Vaart , Jon A. Wellner

Proper splittings of operators are commonly used to study the convergence of iterative processes. In order to approximate solutions of operator equations, in this article we deal with proper splittings of closed range bounded linear…

Functional Analysis · Mathematics 2024-03-18 Guillermina Fongi , María Celeste Gonzalez

We study universal approximation of continuous functionals on compact subsets of products of Hilbert spaces. We prove that any such functional can be uniformly approximated by models that first take finitely many continuous linear…

Machine Learning · Computer Science 2026-02-04 Andrey Krylov , Maksim Penkin

Proximities are at the heart of almost all machine learning methods. If the input data are given as numerical vectors of equal lengths, euclidean distance, or a Hilbertian inner product is frequently used in modeling algorithms. In a more…

Machine Learning · Computer Science 2020-09-01 Maximilian Münch , Michiel Straat , Michael Biehl , Frank-Michael Schleif
‹ Prev 1 3 4 5 6 7 10 Next ›