English
Related papers

Related papers: A note on existence of free Stein kernels

200 papers

We describe a construction of Stein kernels using moment maps, which are solutions to a variant of the Monge-Amp\`ere equation. As a consequence, we show how regularity bounds on these maps control the rate of convergence in the classical…

Probability · Mathematics 2023-06-08 Max Fathi

We present Random Partition Kernels, a new class of kernels derived by demonstrating a natural connection between random partitions of objects and kernels between those objects. We show how the construction can be used to create kernels…

Machine Learning · Statistics 2014-02-19 Alex Davies , Zoubin Ghahramani

We explore connections between covariance representations, Bismut-type formulas and Stein's method. First, using the theory of closed symmetric forms, we derive covariance representations for several well-known probability measures on…

Probability · Mathematics 2023-07-06 Benjamin Arras , Christian Houdré

We introduce kernel estimators for the semicircle law. In this first part of our general theory on the estimators, we prove the consistency and conduct simulation study to show the performance of the estimators. We also point out that…

Mathematical Physics · Physics 2011-07-15 Wang Zhou

Some general criteria to produce explicit free algebras inside the division ring of fractions of skew polynomial rings are presented. These criteria are applied to some special cases of division rings with natural involutions, yielding, for…

Rings and Algebras · Mathematics 2016-05-17 Vitor O. Ferreira , Érica Z. Fornaroli , Jairo Z. Gonçalves

We investigate links between the so-called Stein's density approach in dimension one and some functional and concentration inequalities. We show that measures having a finite first moment and a density with connected support satisfy a…

Probability · Mathematics 2018-11-26 Adrien Saumard

Estimating the score, i.e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable…

Machine Learning · Statistics 2020-07-01 Yuhao Zhou , Jiaxin Shi , Jun Zhu

In the free case, it is possible to define quantum fields which describe particles with integer or half-integer spin larger than one. It is shown that particles with integer spin must have Bose statistic and particles with half-integer-spin…

History and Philosophy of Physics · Physics 2017-04-04 Markus Fierz , Guglielmo Pasa

In this paper we investigate the class of invariant positive definite kernels on the free semigroup on N generators. We provide a combinatorial description of the positivity of the kernel in terms of Dyck paths and then we find a…

Functional Analysis · Mathematics 2007-05-23 T. Banks , T. Constantinescu , Nermine El-Sissi

We study the weighted Poincar\'e constant $C(p,w)$ of a probability density $p$ with weight function $w$ using integration methods inspired by Stein's method. We obtain a new version of the Chen-Wang variational formula which, as a…

Probability · Mathematics 2022-06-13 Gilles Germain , Yvik Swan

Kernel Estimation provides an unbinned and non-parametric estimate of the probability density function from which a set of data is drawn. In the first section, after a brief discussion on parametric and non-parametric methods, the theory of…

High Energy Physics - Experiment · Physics 2009-10-31 Kyle S. Cranmer

We propose a kernel-based nonparametric test of relative goodness of fit, where the goal is to compare two models, both of which may have unobserved latent variables, such that the marginal distribution of the observed variables is…

Machine Learning · Statistics 2023-05-10 Heishiro Kanagawa , Wittawat Jitkrittum , Lester Mackey , Kenji Fukumizu , Arthur Gretton

In a directed graph, a kernel is a subset of vertices that is both stable and absorbing. Not all digraphs have a kernel, but a theorem due to Boros and Gurvich guarantees the existence of a kernel in every clique-acyclic orientation of a…

Discrete Mathematics · Computer Science 2018-01-09 Adèle Pass-Lanneau , Ayumi Igarashi , Frédéric Meunier

A criterion for elements of free Zinbiel algebras to be Lie or Jordan is established. This criterion is used in studying speciality problems of Tortkara algebras. We construct a base of free special Tortkara algebras. Furthermore, we prove…

Rings and Algebras · Mathematics 2019-08-16 Askar Dzhumadil'daev , Nurlan Ismailov , Farukh Mashurov

Over the last 80 years there has been much interest in the problem of finding an explicit formula for the probability density function of two zero mean correlated normal random variables. Motivated by this historical interest, we use a…

Statistics Theory · Mathematics 2021-04-13 Robert E. Gaunt

Realizing free semicircular elements on the full Fock space, we prove an equivalence between rationality of operators obtained from them and finiteness of the rank of their commutators with right annihilation operators. This is an analogue…

Operator Algebras · Mathematics 2022-12-06 Akihiro Miyagawa

The distinction between pure states and mixed states is a kernel ingredient of what is considered to be the standard formulation of quantum mechanics and plays today a kernel role in foundational debates about the meaning of quantum…

History and Philosophy of Physics · Physics 2024-11-01 Christian de Ronde , César Massri

This work presents the concept of kernel mean embedding and kernel probabilistic programming in the context of stochastic systems. We propose formulations to represent, compare, and propagate uncertainties for fairly general stochastic…

Machine Learning · Statistics 2020-05-05 Jia-Jie Zhu , Krikamol Muandet , Moritz Diehl , Bernhard Schölkopf

Free cumulants were introduced as the proper analog of classical cumulants in the theory of free probability. There is a mix of similarities and differences, when one considers the two families of cumulants. Whereas the combinatorics of…

Combinatorics · Mathematics 2015-03-17 Kurusch Ebrahimi-Fard , Frederic Patras

Kernel discrepancies are a powerful tool for analyzing worst-case errors in quasi-Monte Carlo (QMC) methods. Building on recent advances in optimizing such discrepancy measures, we extend the subset selection problem to the setting of…

Machine Learning · Statistics 2025-11-05 Deyao Chen , François Clément , Carola Doerr , Nathan Kirk