Geometry and clustering with metrics derived from separable Bregman divergences
Preprint
Abstract
Separable Bregman divergences induce Riemannian metric spaces that are isometric to the Euclidean space after monotone embeddings. We investigate fixed rate quantization and its codebook Voronoi diagrams, and report on experimental performances of partition-based, hierarchical, and soft clustering algorithms with respect to these Riemann-Bregman distances.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Prediction in Riemannian metrics derived from divergence functionsCommunications in Statistics - Theory and Methods, 2020
- The Bregman distance, approximate compactness and convexity of Chebyshev sets in Banach spacesJournal of Approximation Theory, 2010
- Sided and Symmetrized Bregman CentroidsIEEE Transactions on Information Theory, 2009
- On the Optimality of Conditional Expectation as a Bregman PredictorIEEE Transactions on Information Theory, 2005
- Clustering with Bregman Divergences2004
- Bregman Monotone Optimization AlgorithmsSIAM Journal on Control and Optimization, 2003
- A User's Guide to Measure Theoretic Probability2001
- Math Talks for Undergraduates1999
- Maximum Likelihood from Incomplete Data Via the EM AlgorithmJournal of the Royal Statistical Society Series B: Statistical Methodology, 1977
- The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programmingUSSR Computational Mathematics and Mathematical Physics, 1967