Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Independent statistical observables for ultrametric disordered populations.

B G Giraud1

  • 1Service de Physique Théorique, Centre d'Etudes de Saclay, 91191 Gif sur Yvette, France.

Physical Review. E, Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics
|April 24, 2002
PubMed
Summary

This study shows that random data often exhibits ultrametric covariations. We developed methods to identify robust collective observables even when data labeling is uncertain, improving data analysis in complex systems.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Superadditive correlation.

Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics·2002
Same author

Elementary derivative tasks and neural net multiscale analysis of tasks.

Physical review. E, Statistical, nonlinear, and soft matter physics·2002
Same author

Effects of collateral inhibition in a model of the immature rat cerebellar cortex: multineuron correlations.

Brain research. Cognitive brain research·1993
See all related articles

Area of Science:

  • Statistical Physics
  • Data Analysis
  • Complex Systems

Background:

  • Ultrametricity is a common feature in random data, implying hierarchical structures.
  • Covariance matrices of random data samples can exhibit ultrametric properties.
  • Identifying underlying structures in noisy data is a significant challenge.

Purpose of the Study:

  • To investigate the prevalence and implications of ultrametric covariations in random data.
  • To develop methods for defining independent collective observables from covariance matrices.
  • To identify data analysis techniques robust to labeling uncertainties in hierarchical data.

Main Methods:

  • Diagonalization of the covariance matrix to define collective observables.
  • Analysis of symmetry properties of eigenvectors.

Related Experiment Videos

  • Development of sorting algorithms to enhance robustness against labeling errors.

    • Main Results:

    • Ultrametric covariations are frequently observed in random datasets.
    • Diagonalization provides a way to obtain decorrelated collective observables.
    • Specific observables demonstrate resilience to random perturbations in data labeling.

    Conclusions:

    • The presence of ultrametricity in data can be leveraged for structural analysis.
    • The proposed method allows for the identification of robust collective variables.
    • This approach enhances the reliability of analyzing complex systems with hierarchical organization and potential labeling noise.