Skip to main content

Geometry and Fixed-Rate Quantization in Riemannian Metric Spaces Induced by Separable Bregman Divergences

  • 1518 Accesses

Part of the Lecture Notes in Computer Science book series (LNIP,volume 11712)

Abstract

Dual separable Bregman divergences induce dual Riemannian metric spaces which are isometric to the Euclidean space after non-linear monotone embeddings. We investigate fixed-rate quantization and the induced Voronoi diagrams in those metric spaces.

Keywords

  • Bregman divergence
  • Riemannian metric
  • Legendre transformation
  • Voronoi diagram
  • Quantization

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Amari, S.-i., Nagaoka, H.: Methods of Information Geometry. Translations of Mathematical Monographs, vol. 191. Oxford University Press, New York (2000)

    Google Scholar 

  2. Nielsen, F, Boissonnat, J-D., Nock, F.: On Bregman Voronoi diagrams. In: ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 746–755 (2007)

    Google Scholar 

  3. Boissonnat, J.-D., Nielsen, F., Nock, F.: Bregman Voronoi diagrams. Discret. Comput. Geom. 44, 281–307 (2010)

    CrossRef  MathSciNet  Google Scholar 

  4. Nielsen, F., Nock, R.: Skew Jensen-Bregman Voronoi diagrams. In: Gavrilova, M.L., Tan, C.J.K., Mostafavi, M.A. (eds.) Transactions on Computational Science XIV. LNCS, vol. 6970, pp. 102–128. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25249-5_4

    CrossRef  Google Scholar 

  5. Calin, O., Urdiste, C.: Geometric Modeling in Probability and Statistics. Springer Internl. Pub, Switzerland (2010)

    Google Scholar 

  6. Gzyl, H.: Prediction in Riemannian metrics derived from divergence functions (2018). http://arxiv.org/abs/1808.01638

  7. Linder, T.: Learning-theoretic methods in vector quantization. In: Györfi, L. (ed.) Principles of Nonparametric Learning. CISM, vol. 434, pp. 163–210. Springer, Vienna (2002). https://doi.org/10.1007/978-3-7091-2568-7_4

    CrossRef  Google Scholar 

  8. Nielsen, F., Nock, R.: Sided and symmetrized Bregman centroids. IEEE Trans. Inf. Theory 55(6), 2882–2904 (2009)

    CrossRef  MathSciNet  Google Scholar 

  9. Nielsen, F.: An elementary introduction to information geometry (2018). https://arxiv.org/abs/1808.08271

  10. Pollard, D.: A User’s Guide to Measure Theoretic Probability. Cambridge University Press, Cambridge (2002)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Frank Nielsen .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Gomes-Gonçalves, E., Gzyl, H., Nielsen, F. (2019). Geometry and Fixed-Rate Quantization in Riemannian Metric Spaces Induced by Separable Bregman Divergences. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2019. Lecture Notes in Computer Science(), vol 11712. Springer, Cham. https://doi.org/10.1007/978-3-030-26980-7_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-26980-7_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-26979-1

  • Online ISBN: 978-3-030-26980-7

  • eBook Packages: Computer ScienceComputer Science (R0)