Stochastic Tverberg theorems with applications in multiclass logistic regression, separability, and centerpoints of data

DOI10.1137/19M1277102MaRDI QIDQ5037559zbMATH OpenOpenAlexFDO

Authors Jesús A. De Loera, Thomas A. Hogan

Publication date 1 March 2022

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1907.09698

zbMATH Keywords

logistic regressionmaximum likelihood estimationgeneralized linear modelsgeometric probabilityTverberg's theoremcombinatorial convexityTukey medianhigh-dimensional logistic regressioncenterpointscomputational geometry in statisticsdepth of data pointseparability of data

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02) Generalized linear models (logistic models) (62J12) Pattern recognition, speech recognition (68T10) Geometric probability and stochastic geometry (60D05)

Abstract: We present new stochastic geometry theorems that give bounds on the probability that $m$ random data classes all contain a point in common in their convex hulls. We apply these stochastic separation theorems to obtain bounds on the probability of existence of maximum likelihood estimators in multinomial logistic regression. We also discuss connections to condition numbers for analysis of steepest descent algorithms in logistic regression and to the computation of centerpoints of data clouds.

Recommendations

• On the separability of stochastic geometric objects, with applications
• Stochastic separation theorems
• On the separability of stochastic geometric objects, with applications
• General stochastic separation theorems with optimal bounds
• Robust Tverberg and Colourful Carathéodory Results via Random Choice

Cites work

• scientific article; zbMATH DE number 3167451 (Why is no real title available?)
• scientific article; zbMATH DE number 3746271 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• scientific article; zbMATH DE number 3541764 (Why is no real title available?)
• scientific article; zbMATH DE number 6469174 (Why is no real title available?)
• A Generalization of Radon's Theorem
• A Problem in Geometric Probability.
• A generalisation of Tverberg's theorem
• APPROXIMATING CENTER POINTS WITH ITERATIVE RADON POINTS
• Approximate centerpoints with proofs
• Approximating Tverberg points in linear time for any fixed dimension
• Computational geometry and statistical depth measures
• Enumeration of Seven-Argument Threshold Functions
• Living on the edge: phase transitions in convex programs with random data
• On Sets Projectively Equivalent to the Vertices of a Convex Polytope
• On the existence of maximum likelihood estimates in logistic regression models
• Origin-embracing distributions or a continuous analogue of the upper bound theorem
• Robust Tverberg and Colourful Carathéodory Results via Random Choice
• The discrete yet ubiquitous theorems of Carathéodory, Helly, Sperner, Tucker, and Tverberg
• The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
• The stochastic geometry of unconstrained one-bit data compression
• Tverberg’s theorem is 50 years old: A survey

Cited in

(4)

• Support vector machines and Radon's theorem
• A Model for Birdwatching and other Chronological Sampling Activities
• Algorithms for Radon partitions with tolerance
• Stochastic separation theorems

This page was built for publication: Stochastic Tverberg theorems with applications in multiclass logistic regression, separability, and centerpoints of data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037559)