Skip to main content

(Para-)Holomorphic Connections for Information Geometry

  • Conference paper
  • First Online:
Geometric Science of Information (GSI 2017)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 10589))

Included in the following conference series:

Abstract

On a statistical manifold \((M,g,\nabla )\), the Riemannian metric g is coupled to an (torsion-free) affine connection \(\nabla \), such that \(\nabla g \) is totally symmetric; \(\{\nabla ,g\}\) is said to form “Codazzi coupling”. This leads \(\nabla ^{*}\), the g -conjugate of \(\nabla \), to have same torsion as that of \(\nabla \). In this paper, we investigate how statistical structure interacts with L in an almost Hermitian and almost para-Hermitian manifold (MgL), where L denotes, respectively, an almost complex structure J with \(J^{2}=- \mathrm{id}\) or an almost para-complex structure K with \( K^{2}=\mathrm{id}\). Starting with \(\nabla ^{L}\), the L -conjugate of \(\nabla \), we investigate the interaction of (generally torsion-admitting) \(\nabla \) with L, and derive a necessary and sufficient condition (called “Torsion Balancing” condition) for L to be integrable, hence making (MgL) (para-)Hermitian, and for \(\nabla \) to be (para-)holomorphic. We further derive that \(\nabla ^L\) is (para-)holomorphic if and only if \(\nabla \) is, and that \(\nabla ^*\) is (para-)holomorphic if and only if \(\nabla \) is (para-)holomorphic and Codazzi coupled to g. Our investigations provide concise conditions to extend statistical manifolds to (para-)Hermitian manifolds.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Furuhata, H.: Hypersurfaces in statistical manifolds. Differ. Geom. Appl. 27(3), 420–429 (2009)

    Article  MATH  MathSciNet  Google Scholar 

  2. Henmi, M., Matsuzoe, H.: Geometry of pre-contrast functions and non-conservative estimating functions. In: International Workshop on Complex Structures, Integrability and Vector Fields, vol. 1340, no. 1. AIP Publishing (2011)

    Google Scholar 

  3. Lauritzen, S.L.: Statistical manifolds. In: Differential Geometry in Statistical Inference. IMS Lecture Notes Monograph Series, vol. 10, pp. 163–216. Institute of Mathematical Statistics (1987)

    Google Scholar 

  4. Matsuzoe, H.: Statistical manifolds and geometry of estimating functions. In: Recent Progress in Differential Geometry and Its Related Field, pp. 187–202. World Sci. Publ. (2013)

    Google Scholar 

  5. Moroianu, A.: Lectures on Kähler Geometry. London Mathematical Society Student Texts, vol. 69. Cambridge University Press, Cambridge (2007)

    Book  MATH  Google Scholar 

  6. Nomizu, K., Sasaki, T.: Affine Differential Geometry: Geometry of Affine Immersions. Cambridge Tracts in Mathematics, vol. 111. Cambridge University Press, Cambridge (1994)

    MATH  Google Scholar 

  7. Simon, U.: Affine differential geometry. In: Handbook of Differential Geometry, vol. 1, pp. 905–961. North-Holland (2000)

    Google Scholar 

  8. Schwenk-Schellschmidt, A., Simon, U.: Codazzi-equivalent affine connections. RM 56(1–4), 211–229 (2009)

    MATH  MathSciNet  Google Scholar 

  9. Tao, J., Zhang, J.: Transformations and coupling relations for affine connections. Differ. Geom. Appl. 49, 111–130 (2016)

    Article  MATH  MathSciNet  Google Scholar 

  10. Fei, T., Zhang, J.: Interaction of Codazzi couplings with (para-)Kahler geometry. RM, 05 July 2017. doi:10.1007/s0025-017-0711-7

Download references

Acknowledgement

This research is supported by DARPA/ARO Grant W911NF-16-1-0383 to the University of Michigan (PI: Jun Zhang).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jun Zhang .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Grigorian, S., Zhang, J. (2017). (Para-)Holomorphic Connections for Information Geometry. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2017. Lecture Notes in Computer Science(), vol 10589. Springer, Cham. https://doi.org/10.1007/978-3-319-68445-1_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-68445-1_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-68444-4

  • Online ISBN: 978-3-319-68445-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics