Clustering in Hilbert simplex geometry

@article{Nielsen2017ClusteringIH,
  title={Clustering in Hilbert simplex geometry},
  author={Frank Nielsen and Ke Sun},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.00454}
}
Clustering categorical distributions in the probability simplex is a fundamental task met in many applications dealing with normalized histograms. Traditionally, the differential-geometric structures of the probability simplex have been used either by (i) setting the Riemannian metric tensor to the Fisher information matrix of the categorical distributions, or (ii) defining the dualistic information-geometric structure induced by a smooth dissimilarity measure, the Kullback-Leibler divergence… 
Clustering in Hilbert’s Projective Geometry: The Case Studies of the Probability Simplex and the Elliptope of Correlation Matrices
  • F. Nielsen, Ke Sun
  • Mathematics, Computer Science
    Geometric Structures of Information
  • 2018
TLDR
This work introduces for this clustering task a novel computationally-friendly framework for modeling the probability simplex termed Hilbert simplex geometry, and considers Hilbert’s projective geometry of the elliptope of correlation matrices and study its clustering performances.
Geometry of the probability simplex and its connection to the maximum entropy method
Abstract The use of geometrical methods in statistics has a long and rich history highlighting many different aspects. These methods are usually based on a Riemannian structure defined on the space
On Balls in a Hilbert Polygonal Geometry
Hilbert geometry is a metric geometry that extends the hyperbolic Cayley-Klein geometry. In this video, we explain the shape of balls and their properties in a convex polygonal Hilbert geometry.
Inductive Geometric Matrix Midranges
A-means: improving the cluster assignment phase of k-means for Big Data
TLDR
A new criterion for reducing the processing time of the assignment of data points to clusters for algorithms of the k-means family, when they are applied to instances where the number n of points is large is proposed.
Wasserstein k-means++ for Cloud Regime Histogram Clustering
TLDR
This work generalizes k-means++ guarantees to the Wasserstein setting and provides a scalable minibatch algorithm for Wassersteins clustering, which empirically perform well and lead to new, different cloud regime prototypes.
Manifold Structured Prediction
TLDR
A structured prediction approach to manifold-valued regression is studied and a class of problems for which the considered approach is statistically consistent is characterized and how geometric optimization can be used to compute the corresponding estimator is studied.
Measuring heterogeneity in normative models as the effective number of deviation patterns
TLDR
It is shown that lower effective number of deviation patterns is associated with the presence of systematic differences from a (non-degenerate) normative distribution, and this finding is shown to be consistent across application of a Gaussian process model to synthetic and real-world neuroimaging data.

References

SHOWING 1-10 OF 150 REFERENCES
Clustering in Hilbert’s Projective Geometry: The Case Studies of the Probability Simplex and the Elliptope of Correlation Matrices
  • F. Nielsen, Ke Sun
  • Mathematics, Computer Science
    Geometric Structures of Information
  • 2018
TLDR
This work introduces for this clustering task a novel computationally-friendly framework for modeling the probability simplex termed Hilbert simplex geometry, and considers Hilbert’s projective geometry of the elliptope of correlation matrices and study its clustering performances.
Information geometry connecting Wasserstein distance and Kullback–Leibler divergence via the entropy-relaxed transportation problem
TLDR
A new information-geometrical theory is proposed that provides a unified framework connecting the Wasserstein distance and Kullback–Leibler (KL) divergence and constructed a new one-parameter family of divergences in S_{n-1}$$Sn-1 that are related to both the Wassermann distance and the KL-divergence.
Finding Metric Structure in Information Theoretic Clustering
TLDR
This paper provides the first polynomial-time algorithm for clustering using KL-divergences with provable guarantees for general inputs and finds a “relaxed” metric structure for KL-Divergence.
Information geometry of divergence functions
TLDR
This article studies the differential-geometrical structure of a manifold induced by a divergence function, which consists of a Riemannian metric, and a pair of dually coupled affine connections, which are studied in information geometry.
On Hölder Projective Divergences
TLDR
Two novel classes of Holder divergences and pseudo-divergences that both encapsulate the special case of the Cauchy–Schwarz divergence are presented and closed-form formulas for those statistical dissimilarities when considering distributions belonging to the same exponential family are reported.
The geometric stability of Voronoi diagrams in normed spaces which are not uniformly convex
TLDR
This paper shows that under mild conditions Voronoi diagrams have a certain continuity property, assuming the unit sphere of the space has a certain (non-exotic) structure and the sites satisfy a certain "general position" condition related to it.
Hilbert Space of Probability Density Functions Based on Aitchison Geometry
The set of probability functions is a convex subset of L1 and it does not have a linear space structure when using ordinary sum and multiplication by real constants. Moreover, difficulties arise when
Quantifying the Informativeness of Similarity Measurements
TLDR
An unsupervised measure for quantifying the 'informativeness' of correlation matrices formed from the pairwise similarities or relationships among data instances, which is defined as the distance between a correlation matrix and the nearest correlation matrix with constant off-diagonal entries is described.
Information geometry and its applications
  • F. Opitz
  • Mathematics
    2012 9th European Radar Conference
  • 2012
Information geometry is a new mathematical discipline which applies the methodology of differential geometry to statistics. Therefore, families of exponential distributions are considered as embedded
Voronoi diagrams in higher dimensions under certain polyhedral distance functions
Abstract. The paper bounds the combinatorial complexity of the Voronoi diagram of a set of points under certain polyhedral distance functions. Specifically, if S is a set of n points in general
...
...