Biometrika Jan 27, 2026

Generalized Fréchet means with random minimizing domains and its strong consistency

Authors
Jaesung Park Sungkyu Jung
Research Topics
Machine Learning
Paper Information
  • Journal:
    Biometrika
  • DOI:
    10.1093/biomet/asag002
  • Published:
    January 27, 2026
  • Added to Tracker:
    Feb 10, 2026
Abstract

Abstract This paper introduces a novel extension of Fréchet means, referred to as generalized Fréchet means, as a comprehensive framework for describing the characteristics of random elements. The generalized Fréchet mean is defined as the minimizer of a cost function, and the framework encompasses various extensions of Fréchet means that have appeared in the literature. The most distinctive feature of the proposed framework is that it allows the domain of minimization for the empirical generalized Fréchet means to be random and different from that of its population counterpart. This flexibility broadens the applicability of the Fréchet mean framework to various statistical scenarios, including sequential dimension reduction for non-Euclidean data. We establish a strong consistency theorem for generalized Fréchet means and demonstrate the utility of the proposed framework by verifying the consistency of principal geodesic analysis on the hypersphere.

Author Details
Jaesung Park
Author
Sungkyu Jung
Author
Research Topics & Keywords
Machine Learning
Research Area
Citation Information
APA Format
Jaesung Park & Sungkyu Jung (2026) . Generalized Fréchet means with random minimizing domains and its strong consistency. Biometrika , 10.1093/biomet/asag002.
BibTeX Format
@article{paper866,
  title = { Generalized Fréchet means with random minimizing domains and its strong consistency },
  author = { Jaesung Park and Sungkyu Jung },
  journal = { Biometrika },
  year = { 2026 },
  doi = { 10.1093/biomet/asag002 },
  url = { https://doi.org/10.1093/biomet/asag002 }
}