Doctoral thesis
Open access

Information geometry and data manifold representations

ContributorsSun, Ke
Defense date2015-12-17

Information geometry studies the measurements of intrinsic information based on the mathematical discipline of differential geometry. This dissertation built several new connections between information geometry and machine learning. A Riemannian geometry of a representation manifold R is studied, where each point is a pair-wise (dis-)similarity matrix corresponding to a set of objects. A Riemannian metric of R is derived in closed form based on the Fisher information metric. This metric is featured by emphasizing local information. Information geometric measurements for manifold learning are therefore defined. Statistical mixture learning of the data manifold is viewed as a multi-body problem on a statistical manifold M, where each body is a mixture component, or a point on M. Principles based on geometric compactness can lead to effective regularization for both kernel density estimation and parametric mixture learning. New insights are given on the connection between information geometry, mixture learning, and minimum description length.

  • Machine Learning
  • Information Geometry
  • Dimensionality Reduction
  • Data Visualization
  • Mixture Modelling
  • Sparsity
  • Minimum Description Length
  • Manifold Learning
  • Density Estimation
Research group
Citation (ISO format)
SUN, Ke. Information geometry and data manifold representations. 2015. doi: 10.13097/archive-ouverte/unige:80017
Main files (1)

Technical informations

Creation01/10/2016 5:54:00 PM
First validation01/10/2016 5:54:00 PM
Update time03/15/2023 12:06:11 AM
Status update03/15/2023 12:06:10 AM
Last indexation01/29/2024 8:40:32 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack