Mode and Ridge Estimation in Euclidean and Directional Product Spaces: A Mean Shift Approach

Abstract The set of local modes and density ridge lines are important summary characteristics of the data-generating distribution. In this work, we focus on estimating local modes and density ridges from point cloud data in a product space combining two or more Euclidean and/or directional metric spaces. Specifically, our approach extends the (subspace constrained) mean shift algorithm to such product spaces, addressing potential challenges in the generalization process. We establish the algorithmic convergence of the proposed methods, along with practical implementation guidelines. Experiments on simulated and real-world datasets demonstrate the effectiveness of our proposed methods. Supplementary materials for this article are available online.

• Publication year

  2021

• Venue

  Journal of Computational And Graphical Statistics

• Publication date

  2021-10-16

• Fields of study

  Mathematics, Computer Science, Medicine

• Identifiers
  DOI 10.1080/10618600.2025.2505734arXiv 2110.08505PMID 40881309PMCID PMC12383232
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Kernel density estimation with polyspherical data and its applications

  2024cited by this paper
• Convergence Analysis of Mean Shift

  2023cited by this paper
• sconce: a cosmic web finder for spherical and conic geometries.

  2022cited by this paper
• Bump hunting through density curvature features

  2022cited by this paper
• Mode estimation on matrix manifolds: Convergence and robustness

  2022cited by this paper
• Algorithms for ridge estimation with convergence guarantees

  2021cited by this paper
• Linear convergence of the subspace constrained mean shift algorithm: from Euclidean to directional data.

  2021cited by this paper
• The EM Perspective of Directional Mean Shift Algorithm

  2021cited by this paper
• The 16th Data Release of the Sloan Digital Sky Surveys: First Release from the APOGEE-2 Southern Survey and Full Release of eBOSS Spectra

  2020influential reference
• Product Manifold Learning

  2020cited by this paper
• On the correlation between solar activity and large earthquakes worldwide

  2020cited by this paper
• Kernel Smoothing, Mean Shift, and Their Learning Theory with Directional Data

  2020cited by this paper
• Gaia Data Release 2

  2018cited by this paper
• Gaia Data Release 2. Summary of the contents and survey properties

  2018cited by this paper
• The Modal Age of Statistics

  2018cited by this paper
• Ray: A Distributed Framework for Emerging AI Applications

  2017influential reference
• An Introduction to Topological Data Analysis: Fundamental and Practical Aspects for Data Scientists

  2017cited by this paper
• Firefly (Fitting IteRativEly For Likelihood analYsis): a full spectral fitting code

  2017cited by this paper
• Stellar population properties for 2 million galaxies from SDSS DR14 and DEEP2 DR4 from full spectral fitting

  2017cited by this paper
• A tutorial on kernel density estimation and recent advances

  2017cited by this paper
• On the Estimation of the Gradient Lines of a Density and the Consistency of the Mean-Shift Algorithm

  2016cited by this paper
• First-order Methods for Geodesically Convex Optimization

  2016cited by this paper
• A sufficient condition for the convergence of the mean shift algorithm with Gaussian kernel

  2015influential reference
• Coordinate descent algorithms

  2015cited by this paper
• A review of mean-shift algorithms for clustering

  2015cited by this paper
• THE SDSS-IV EXTENDED BARYON OSCILLATION SPECTROSCOPIC SURVEY: OVERVIEW AND EARLY DATA

  2015cited by this paper
• Evolution of the cosmic web

  2014cited by this paper
• Generalized Mode and Ridge Estimation

  2014influential reference
• Semi-Supervised Kernel Mean Shift Clustering

  2014cited by this paper
• A Comprehensive Approach to Mode Clustering

  2014cited by this paper
• Asymptotic theory for density ridges

  2014cited by this paper
• Detection of stacked filament lensing between SDSS luminous red galaxies

  2014cited by this paper
• Central limit theorems for directional and linear random variables with applications

  2014cited by this paper
• ALIGNMENTS OF GALAXIES WITHIN COSMIC FILAMENTS FROM SDSS DR7

  2013cited by this paper
• On some convergence properties of the subspace constrained mean shift

  2013cited by this paper
• Detecting filamentary pattern in the cosmic web: a catalogue of filaments for the SDSS

  2013cited by this paper
• Testing the Manifold Hypothesis

  2013cited by this paper
• Exact risk improvement of bandwidth selectors for kernel density estimation with directional data

  2013cited by this paper
• A comparison of bandwidth selectors for mean shift clustering

  2013influential reference
• Introduction to manifold learning

  2012cited by this paper
• Data-driven density derivative estimation, with applications to nonparametric clustering and bump hunting

  2012cited by this paper
• Kernel density estimation for directional-linear data

  2012cited by this paper
• Nonparametric Ridge Estimation

  2012influential reference
• Locally Defined Principal Curves and Surfaces

  2011cited by this paper
• Kernel density estimation on the torus

  2011cited by this paper
• ASYMPTOTICS FOR GENERAL MULTIVARIATE KERNEL DENSITY DERIVATIVE ESTIMATORS

  2011cited by this paper
• Directional Statistics, I

  2011cited by this paper
• Influences of solar cycles on earthquakes

  2011cited by this paper
• Directional mean shift and its application for topology classification of local 3D structures

  2010cited by this paper
• Differential Geometry of Curves and Surfaces

  2010cited by this paper
• Intrinsic mean shift for clustering on Stiefel and Grassmann manifolds

  2009cited by this paper
• Nonlinear Mean Shift over Riemannian Manifolds

  2009cited by this paper
• Optimization algorithms on matrix manifolds

  2009influential reference
• THE SPIN AND ORIENTATION OF DARK MATTER HALOS WITHIN COSMIC FILAMENTS

  2009cited by this paper
• The EM Algorithm and Extensions: Second Edition

  2008cited by this paper
• A note on the convergence of the mean shift

  2007cited by this paper
• Gaussian Mean-Shift Is an EM Algorithm

  2007cited by this paper
• Intrinsic Statistics on Riemannian Manifolds: Basic Tools for Geometric Measurements

  2006influential reference
• The large-scale structure of the Universe

  2006cited by this paper
• Nonlinear Mean Shift for Clustering over Analytic Manifolds

  2006cited by this paper
• Support vector machines for prediction of dihedral angle regions

  2006cited by this paper
• Real-Time Density and Mode Estimation With Application to Time-Dynamic Mode Tracking

  2006cited by this paper
• All of Nonparametric Statistics (Springer Texts in Statistics)

  2006cited by this paper
• Clustering on the Unit Hypersphere using von Mises-Fisher Distributions

  2005influential reference
• Uniform in bandwidth consistency of kernel-type function estimators

  2005cited by this paper
• Multi-scale clustering for gene expression profiling data

  2005cited by this paper
• The law of the iterated logarithm for the multivariate kernel mode estimator

  2003influential reference
• Rates of strong uniform consistency for multivariate kernel density estimators

  2002cited by this paper
• Mean Shift: A Robust Approach Toward Feature Space Analysis

  2002cited by this paper
• Central limit theorem for integrated square error of kernel estimators of spherical density

  2001cited by this paper
• Estimation of Densities and Derivatives of Densities with Directional Data

  2000cited by this paper
• Distance measures in cosmology

  1999cited by this paper
• Riemannian Manifolds: An Introduction to Curvature

  1997cited by this paper
• Ridges in Image and Data Analysis

  1996cited by this paper
• Multivariate Density Estimation

  1996cited by this paper
• Mean Shift, Mode Seeking, and Clustering

  1995cited by this paper
• Bias reduction in kernel density estimation by smoothed empirical transformations

  1994cited by this paper
• Transformations to reduce boundary bias in kernel density estimation

  1994cited by this paper
• Comparison of Smoothing Parameterizations in Bivariate Kernel Density Estimation

  1993cited by this paper
• Multivariate Density Estimation, Theory, Practice and Visualization

  1992cited by this paper
• Kernel estimators of density function of directional data

  1988cited by this paper
• On weak convergence and optimality of kernel density estimates of the mode

  1988influential reference
• Density Estimation for Statistics and Data Analysis

  1987cited by this paper
• Kernel density estimation with spherical data

  1987cited by this paper
• A Slice of the Universe

  1985cited by this paper
• ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM

  1983cited by this paper
• The estimation of the gradient of a density function, with applications in pattern recognition

  1975cited by this paper
• On Estimation of a Probability Density Function and Mode

  1962cited by this paper
• On Lunar and Solar Periodicities of Earthquakes

  1897cited by this paper

• ANALYZING ANIMAL ESCAPE DATA WITH CIRCULAR NONPARAMETRIC MULTIMODAL REGRESSION

  2022cites this paper