English
Related papers

Related papers: Positive Gaussian kernels also have Gaussian minim…

200 papers

We develop some theoretical results for a robust similarity measure named "generalized min-max" (GMM). This similarity has direct applications in machine learning as a positive definite kernel and can be efficiently computed via…

Methodology · Statistics 2016-08-02 Ping Li , Cun-Hui Zhang

Necessary and sufficient conditions for positive Toeplitz operators on the Bergman space of a minimal bounded homogeneous domain to be bounded or compact are described in terms of the Berezin transform, the averaging function and the…

Functional Analysis · Mathematics 2010-10-22 Satoshi Yamaji

It was observed recently in work of Bez, Buschenhenke, Cowling, Flock and the first author, that the euclidean Brascamp-Lieb inequality satisfies a natural and useful Fourier duality property. The purpose of this paper is to establish an…

Classical Analysis and ODEs · Mathematics 2020-11-30 Jonathan Bennett , Eunhee Jeong

We derive novel anti-concentration bounds for the difference between the maximal values of two Gaussian random vectors across various settings. Our bounds are dimension-free, scaling with the dimension of the Gaussian vectors only through…

Statistics Theory · Mathematics 2024-08-27 Alexandre Belloni , Ethan X. Fang , Shuting Shen

This paper is concerned with volume-constrained minimization problems derived from Gamow's liquid drop model for the atomic nucleus, involving the competition of a perimeter term and repulsive nonlocal potentials. We consider a large class…

Analysis of PDEs · Mathematics 2021-05-04 Marc Pegon

The kernel function and its hyperparameters are the central model selection choice in a Gaussian proces (Rasmussen and Williams, 2006). Typically, the hyperparameters of the kernel are chosen by maximising the marginal likelihood, an…

Machine Learning · Statistics 2022-11-07 Vidhi Lalchand , Wessel P. Bruinsma , David R. Burt , Carl E. Rasmussen

A common way of characterizing minimax estimators in point estimation is by moving the problem into the Bayesian estimation domain and finding a least favorable prior distribution. The Bayesian estimator induced by a least favorable prior,…

Machine Learning · Statistics 2022-02-24 Alex Dytso , Mario Goldenbaum , H. Vincent Poor , Shlomo Shamai

We consider multivariate approximation problems in the average case setting with a zero mean Gaussian measure whose covariance kernel is a periodic Gevrey kernel. We investigate various notions of algebraic tractability and exponential…

Numerical Analysis · Mathematics 2024-12-20 Wanting Lu , Heping Wang

We discuss the notion of optimal polynomial approximants in multivariable reproducing kernel Hilbert spaces. In particular, we analyze difficulties that arise in the multivariable case which are not present in one variable, for example, a…

Complex Variables · Mathematics 2022-05-03 Meredith Sargent , Alan Sola

In the context of variable exponent Lebesgue spaces equipped with a lower Ahlfors measure we obtain weighted norm inequalities over bounded domains for the centered fractional maximal function and the fractional integral operator.

Analysis of PDEs · Mathematics 2009-07-31 Osvaldo Gorosito , Gladis Pradolini , Oscar Salinas

The tensor and exterior squares of a completely continuous non-negative linear operator $A$ acting in the ideal space $X(\Omega)$ are studied. The theorem representing the point spectrum (except, probably, zero) of the tensor square $A…

Spectral Theory · Mathematics 2008-12-05 Olga Y. Kushel , Petr P. Zabreiko

We give a simple proof of a lower bound for the Dirichlet heat kernel in terms of the Gaussian heat kernel. Using this we establish a non-existence result for semilinear heat equations with zero Dirichlet boundary conditions and initial…

Analysis of PDEs · Mathematics 2013-07-26 Robert Laister , James C. Robinson , Mikolaj Sierzega

We study the convergence properties of the Gibbs Sampler in the context of posterior distributions arising from Bayesian analysis of conditionally Gaussian hierarchical models. We develop a multigrid approach to derive analytic expressions…

Computation · Statistics 2019-06-27 Giacomo Zanella , Gareth Roberts

Shortened abstract: Given a constrained minimization problem, under what conditions does there exist a related, unconstrained problem having the same minimum points? This basic question in global optimization motivates this paper, which…

Statistical Mechanics · Physics 2007-05-23 M. Costeniuc , R. S. Ellis , H. Touchette , B. Turkington

We present a novel kernel over the space of probability measures based on the dual formulation of optimal regularized transport. We propose an Hilbertian embedding of the space of probabilities using their Sinkhorn potentials, which are…

Machine Learning · Statistics 2022-10-14 François Bachoc , Louis Béthune , Alberto Gonzalez-Sanz , Jean-Michel Loubes

We deal with the boundedness properties of higher order commutators related to some generalizations of the multilinear fractional integral operator of order $m$, $I_\alpha ^m$, from a product of weighted Lebesgue spaces into adequate…

Classical Analysis and ODEs · Mathematics 2022-10-07 Fabio Berra , Gladis Pradolini , Jorgelina Recchi

We extend the classical Lebesgue-Riesz norm estimations for integral operators acting between different classical Lebesgue-Riesz spaces into the Grand Lebesgue Spaces, in the general case. As an example we consider matrix operators acting…

Functional Analysis · Mathematics 2023-08-17 Maria Rosaria Formica , Eugeny Ostrovsky , Leonid Sirota

Bayesian optimisation has gained great popularity as a tool for optimising the parameters of machine learning algorithms and models. Somewhat ironically, setting up the hyper-parameters of Bayesian optimisation methods is notoriously hard.…

Machine Learning · Statistics 2014-07-01 Ziyu Wang , Nando de Freitas

We derive improved regression and classification rates for support vector machines using Gaussian kernels under the assumption that the data has some low-dimensional intrinsic structure that is described by the box-counting dimension. Under…

Statistics Theory · Mathematics 2021-04-08 Thomas Hamm , Ingo Steinwart

We prove upper and lower bounds for the number of eigenvalues of semi-bounded Schr\"odinger operators in all spatial dimensions. As a corollary, we obtain two-sided estimates for the sum of the negative eigenvalues of atomic Hamiltonians…

Mathematical Physics · Physics 2024-09-16 Sven Bachmann , Richard Froese , Severin Schraven
‹ Prev 1 8 9 10 Next ›