English
Related papers

Related papers: Kullback Leibler property of kernel mixture priors…

200 papers

In this work, we present formulations for regularized Kullback-Leibler and R\'enyi divergences via the Alpha Log-Determinant (Log-Det) divergences between positive Hilbert-Schmidt operators on Hilbert spaces in two different settings,…

Machine Learning · Statistics 2022-07-19 Minh Ha Quang

In finite mixture models, apart from underlying mixing measure, true kernel density function of each subpopulation in the data is, in many scenarios, unknown. Perhaps the most popular approach is to choose some kernel functions that we…

Statistics Theory · Mathematics 2017-09-26 Nhat Ho , XuanLong Nguyen , Ya'acov Ritov

The Kullback-Leibler (KL) divergence is a fundamental equation of information theory that quantifies the proximity of two probability distributions. Although difficult to understand by examining the equation, an intuition and understanding…

Information Theory · Computer Science 2014-04-09 Jonathon Shlens

Kernels are efficient in representing nonlocal dependence and they are widely used to design operators between function spaces. Thus, learning kernels in operators from data is an inverse problem of general interest. Due to the nonlocal…

Machine Learning · Statistics 2024-10-21 Neil K. Chada , Quanjun Lang , Fei Lu , Xiong Wang

This paper introduces a novel approach to probabilistic deep learning, kernel density matrices, which provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random…

Machine Learning · Computer Science 2024-05-01 Fabio A. González , Raúl Ramos-Pollán , Joseph A. Gallego-Mejia

We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors and proceeds using a simple…

Machine Learning · Computer Science 2020-07-14 Sebastian Claici , Mikhail Yurochkin , Soumya Ghosh , Justin Solomon

We give a short proof of the $L^{1}$ criterion for Beurling generalized integers to have a positive asymptotic density. We actually prove the existence of density under a weaker hypothesis. We also discuss related sufficient conditions for…

Number Theory · Mathematics 2019-08-13 Gregory Debruyne , Jasson Vindas

In 1997 H.G.Diamond gave a condition on Beurling's generalized prime numbers in order that the corresponding generalized integers have a density. We give a new proof of this condition (Theorem 1) and a proof that it is not necessary…

Number Theory · Mathematics 2016-11-15 Jean-Pierre Kahane

A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. Two contributing factors, the underspecification of the model and…

Machine Learning · Statistics 2022-05-10 Gábor Melis , András György , Phil Blunsom

We derive necessary density conditions for sampling and for interpolation in general reproducing kernel Hilbert spaces satisfying some natural conditions on the geometry of the space and the reproducing kernel. If the volume of shells is…

Functional Analysis · Mathematics 2018-04-03 Hartmut Führ , Karlheinz Gröchenig , Antti Haimi , Andreas Klotz , José Luis Romero

In binary-transaction data-mining, traditional frequent itemset mining often produces results which are not straightforward to interpret. To overcome this problem, probability models are often used to produce more compact and conclusive…

Machine Learning · Computer Science 2012-09-27 Ruefei He , Jonathan Shapiro

In a Bayesian context, prior specification for inference on monotone densities is conceptually straightforward, but proving posterior convergence theorems is complicated by the fact that desirable prior concentration properties often are…

Statistics Theory · Mathematics 2020-07-28 Ryan Martin

An initial screening experiment may lead to ambiguous conclusions regarding the factors which are active in explaining the variation of an outcome variable: thus adding follow-up runs becomes necessary. We propose a fully Bayes objective…

Methodology · Statistics 2014-05-13 Guido Consonni , Laura Deldossi

This paper deals with the taking into account a given set of realizations as constraints in the Kullback-Leibler minimum principle, which is used as a probabilistic learning algorithm. This permits the effective integration of data into…

Machine Learning · Statistics 2022-05-09 Christian Soize

Let L be an ample holomorphic line bundle over a compact complex Hermitian manifold X. Any fixed smooth Hermitian metric on L induces a Hilbert space structure on the space of global holomorphic sections with values in the k:th tensor power…

Complex Variables · Mathematics 2007-05-23 Robert Berman

In this work, we are concerned with the estimation of the predictive density of a Gaussian random vector where both the mean and the variance are unknown. In such a context, we prove the inadmissibility of the best equivariant predictive…

Statistics Theory · Mathematics 2014-05-27 Aurélie Boisbunon , Yuzo Maruyama

We study classes of reproducing kernels $K$ on general domains; these are kernels which arise commonly in machine learning models; models based on certain families of reproducing kernel Hilbert spaces. They are the positive definite kernels…

Functional Analysis · Mathematics 2017-08-22 Palle Jorgensen , Feng Tian

This paper introduces the kernel mixture network, a new method for nonparametric estimation of conditional probability densities using neural networks. We model arbitrarily complex conditional densities as linear combinations of a family of…

Machine Learning · Statistics 2017-05-22 Luca Ambrogioni , Umut Güçlü , Marcel A. J. van Gerven , Eric Maris

Estimating the marginal likelihoods is an essential feature of model selection in the Bayesian context. It is especially crucial to have good estimates when assessing the number of planets orbiting stars when the models explain the noisy…

Earth and Planetary Astrophysics · Physics 2015-06-03 Mikko Tuomi , Hugh R. A. Jones

We study frequentist properties of Bayesian and $L_0$ model selection, with a focus on (potentially non-linear) high-dimensional regression. We propose a construction to study how posterior probabilities and normalized $L_0$ criteria…

Statistics Theory · Mathematics 2021-10-07 David Rossell
‹ Prev 1 4 5 6 7 8 10 Next ›