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

DOI10.1137/19M1277102zbMATH Open1485.60014arXiv1907.09698OpenAlexW3111520617MaRDI QIDQ5037559FDOQ5037559

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)

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.

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

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

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)

Cites Work

• Title not available (Why is that?)
• On the existence of maximum likelihood estimates in logistic regression models
• Title not available (Why is that?)
• Enumeration of Seven-Argument Threshold Functions
• A generalisation of Tverberg's theorem
• Living on the edge: phase transitions in convex programs with random data
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Generalization of Radon's Theorem
• A Problem in Geometric Probability.
• APPROXIMATING CENTER POINTS WITH ITERATIVE RADON POINTS
• Approximate centerpoints with proofs
• On Sets Projectively Equivalent to the Vertices of a Convex Polytope
• Title not available (Why is that?)
• Tverberg’s theorem is 50 years old: A survey
• Robust Tverberg and Colourful Carathéodory Results via Random Choice
• Computational geometry and statistical depth measures
• The stochastic geometry of unconstrained one-bit data compression
• The discrete yet ubiquitous theorems of Carathéodory, Helly, Sperner, Tucker, and Tverberg
• Approximating Tverberg points in linear time for any fixed dimension
• The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
• Origin-embracing distributions or a continuous analogue of the upper bound theorem

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)