Gaussian determinantal processes: a new model for directionality in data

DOI10.1073/PNAS.1917151117MaRDI QIDQ5073075zbMATH OpenOpenAlexWikidataFDO

Authors Subhroshekhar Ghosh, Philippe Rigollet

Publication date 5 May 2022

Published in Proceedings of the National Academy of Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2111.09990

Mathematics Subject Classification ID

Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55) Factor analysis and principal components; correspondence analysis (62H25)

Abstract: Determinantal point processes (a.k.a. DPPs) have recently become popular tools for modeling the phenomenon of negative dependence, or repulsion, in data. However, our understanding of an analogue of a classical parametric statistical theory is rather limited for this class of models. In this work, we investigate a parametric family of Gaussian DPPs with a clearly interpretable effect of parametric modulation on the observed points. We show that parameter modulation impacts the observed points by introducing directionality in their repulsion structure, and the principal directions correspond to the directions of maximal (i.e. the most long ranged) dependency. This model readily yields a novel and viable alternative to Principal Component Analysis (PCA) as a dimension reduction tool that favors directions along which the data is most spread out. This methodological contribution is complemented by a statistical analysis of a spiked model similar to that employed for covariance matrices as a framework to study PCA. These theoretical investigations unveil intriguing questions for further examination in random matrix theory, stochastic geometry and related topics.

Recommendations

• Determinantal point process models and statistical inference
• Quantifying repulsiveness of determinantal point processes
• Determinantal point processes for machine learning
• Determinantal point process models on the sphere
• On a few statistical applications of determinantal point processes

Cites work

• A model for the bus system in Cuernavaca (Mexico)
• Asymptotics of sample eigenstructure for a large dimensional spiked covariance model
• Characteristic vectors of bordered matrices with infinite dimensions
• Determinantal point process models and statistical inference
• Determinantal point processes
• Determinantal point processes for machine learning
• scientific article; zbMATH DE number 1713116 (Why is no real title available?)
• scientific article; zbMATH DE number 4062374 (Why is no real title available?)
• scientific article; zbMATH DE number 2174437 (Why is no real title available?)
• Introduction to nonparametric estimation
• Multisurface method of pattern separation for medical diagnosis applied to breast cytology.
• Numerical inverting of matrices of high order
• On the distribution of the largest eigenvalue in principal components analysis
• Optimal detection of sparse principal components in high dimension
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Principal component analysis: a review and recent developments
• Random Matrices in Physics
• Some open problems in random matrix theory and the theory of integrable systems
• Some open problems in random matrix theory and the theory of integrable systems. II
• The concentration of measure phenomenon
• The Dyson and Coulomb games
• The largest eigenvalues of sample covariance matrices for a spiked population: diagonal case
• The statistical properties of the city transport in Cuernavaca (Mexico) and random matrix ensembles
• Universality in numerical computations with random data
• Zeros of Gaussian analytic functions and determinantal point processes

Cited in

(4)

• The Poisson binomial distribution -- old \& new
• Determinantal point process models and statistical inference
• Approximate Gibbsian structure in strongly correlated point fields and generalized Gaussian zero ensembles
• Modeling Hypergraphs with Diversity and Heterogeneous Popularity

This page was built for publication: Gaussian determinantal processes: a new model for directionality in data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5073075)