English
Related papers

Related papers: Determinantal probability measures on Grassmannian…

200 papers

Stochastic gradient descent (SGD) is a cornerstone of machine learning. When the number N of data items is large, SGD relies on constructing an unbiased estimator of the gradient of the empirical risk using a small subset of the original…

Machine Learning · Statistics 2021-12-14 Remi Bardenet , Subhro Ghosh , Meixia Lin

Positive and negative dependence are fundamental concepts that characterize the attractive and repulsive behavior of random subsets. Although some probabilistic models are known to exhibit positive or negative dependence, it is challenging…

Machine Learning · Statistics 2025-02-11 Takahiro Kawashima , Hideitsu Hino

We define a class of random measures, spatially independent martingales, which we view as a natural generalisation of the canonical random discrete set, and which includes as special cases many variants of fractal percolation and Poissonian…

Classical Analysis and ODEs · Mathematics 2015-02-27 Pablo Shmerkin , Ville Suomala

Determinantal point processes (DPPs) offer a powerful approach to modeling diversity in many applications where the goal is to select a diverse subset. We study the problem of learning the parameters (the kernel matrix) of a DPP from…

Machine Learning · Statistics 2014-11-10 Boqing Gong , Wei-lun Chao , Kristen Grauman , Fei Sha

We study conditions so that the determinantal point process $\Lambda_\phi$ associated to a generalized Fock space defined by a doubling subharmonic weight $\phi$ is almost surely a separated sequence in $\mathbb C$. Under a natural…

Complex Variables · Mathematics 2025-02-11 Giuseppe Lamberti , Xavier Massaneda

We study the asymptotic behavior of discrete measures on S^{n-1} that are induced by radially projecting point masses concentrated on the integral lattice-points within dilates of a compact body D, for various classes of D. The results…

Number Theory · Mathematics 2007-05-23 Marina Nechayeva , Burton Randol

We introduce Deep Sigma Point Processes, a class of parametric models inspired by the compositional structure of Deep Gaussian Processes (DGPs). Deep Sigma Point Processes (DSPPs) retain many of the attractive features of (variational)…

Machine Learning · Statistics 2020-12-29 Martin Jankowiak , Geoff Pleiss , Jacob R. Gardner

Often we consider machine learning models or statistical analysis methods which we endeavour to alter, by introducing a randomized mechanism, to make the model conform to a differential privacy constraint. However, certain models can often…

Machine Learning · Computer Science 2024-05-24 Jack Fitzsimons , Agustín Freitas Pasqualini , Robert Pisarczyk , Dmitrii Usynin

Determinantal Point Processes (DPPs) are popular models for point processes with repulsion. They appear in numerous contexts, from physics to graph theory, and display appealing theoretical properties. On the more practical side of things,…

Statistics Theory · Mathematics 2018-08-22 Simon Barthelmé , Pierre-Olivier Amblard , Nicolas Tremblay

Determinantal point processes (DPPs) are specific probability distributions over clouds of points that are used as models and computational tools across physics, probability, statistics, and more recently machine learning. Sampling from…

Machine Learning · Computer Science 2022-03-22 Guillaume Gautier , Guillermo Polito , Rémi Bardenet , Michal Valko

We discuss asymptotic properties of a family of discrete probability measures which may be used to model particle configurations with a wall on a set of discrete nodes. The correlations are shown to be determinantal and are expressed in…

Probability · Mathematics 2015-03-17 Uwe Schwerdtfeger

Discrete random probability measures and the exchangeable random partitions they induce are key tools for addressing a variety of estimation and prediction problems in Bayesian inference. Indeed, many popular nonparametric priors, such as…

Statistics Theory · Mathematics 2015-03-03 P. De Blasi , S. Favaro , A. Lijoi , R. H. Mena , I. Pruenster , M. Ruggiero

Determinantal point processes (DPPs) are an important concept in random matrix theory and combinatorics. They have also recently attracted interest in the study of numerical methods for machine learning, as they offer an elegant "missing…

Machine Learning · Computer Science 2018-04-18 Philipp Hennig , Roman Garnett

A determinantal point process is a stochastic point process that is commonly used to capture negative correlations. It has become increasingly popular in machine learning in recent years. Sampling a determinantal point process however…

Numerical Analysis · Mathematics 2020-09-02 Lexing Ying

For a broad class of point processes, including determinantal point processes, we construct associated marked and conditional ensembles, which allow to study a random configuration in the point process, based on information about a randomly…

Probability · Mathematics 2022-11-01 Tom Claeys , Gabriel Glesner

In this paper we propose a method to construct probability measures on the space of convex bodies with a given pushforward distribution. Concretely we show that there is a measure on the metric space of centrally symmetric convex bodies,…

Probability · Mathematics 2012-04-27 Á. G. Horváth

We study a class of Piecewise Deterministic Markov Processes with state space Rd x E where E is a finite set. The continuous component evolves according to a smooth vector field that is switched at the jump times of the discrete coordinate.…

Probability · Mathematics 2014-04-08 Michel Benaïm , Stéphane Le Borgne , Florent Malrieu , Pierre-André Zitt

The main result of this paper states that if $(N, \Pi)$ is a pair of independent point processes on a common ground space with $N$ Poisson and $\Pi$ determinantal induced by a locally trace class (not necessarily self-adjoint) correlation…

Probability · Mathematics 2017-10-27 Yanqi Qiu

In this brief paper the probability density of a random real, complex and quaternion determinant is rederived using singular values. The behaviour of suitably rescaled random determinants is studied in the limit of infinite order of the…

Statistical Mechanics · Physics 2009-10-31 Giovanni M. Cicuta , Madan L. Mehta

This work is concerned with the quantification of the epistemic uncertainties induced the discretization of partial differential equations. Following the paradigm of probabilistic numerics, we quantify this uncertainty probabilistically.…

Probability · Mathematics 2016-07-14 Ilias Bilionis