Skip to main content

Rényi Relative Entropy from Homogeneous Kullback-Leibler Divergence Lagrangian

  • Conference paper
  • First Online:
Geometric Science of Information (GSI 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 12829))

Included in the following conference series:

Abstract

We study the homogeneous extension of the Kullback-Leibler divergence associated to a covariant variational problem on the statistical bundle. We assume a finite sample space. We show how such a divergence can be interpreted as a Finsler metric on an extended statistical bundle, where the time and the time score are understood as extra random functions defining the model—-. We find a relation between the homogeneous generalisation of the Kullback-Leibler divergence and the Rényi relative entropy, the Rényi parameter being related to the time-reparametrization lapse of the Lagrangian model. We investigate such intriguing relation with an eye to applications in physics and quantum information theory.

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

Access this chapter

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

Institutional subscriptions

References

  1. Amari, S., Nagaoka, H.: Methods of information geometry. American Mathematical Society (2000). (Translated from the 1993 Japanese Original by D. Harada)

    Google Scholar 

  2. Bernamonti, A., Galli, F., Myers, R.C., Oppenheim, J.: Holographic second laws of black hole thermodynamics. J. High Energy Phys. 2018(7), 111 (2018). https://doi.org/10.1007/JHEP07(2018)111

    Article  MathSciNet  MATH  Google Scholar 

  3. Brandão, F., Horodecki, M., Ng, N., Oppenheim, J., Wehner, S.: The second laws of quantum thermodynamics. Proc. Natl. Acad. Sci. 112(11), 3275–3279 (2015). https://doi.org/10.1073/pnas.1411728112

  4. Chern, S.-S., Chen, W., Lam, W.K.: Lectures on Differential Geometry. World Scientific, Singapore (1999)

    Google Scholar 

  5. Chirco, G., Malagò, L., Pistone, G.: Lagrangian and Hamiltonian mechanics for probabilities on the statistical manifold. arXiv:2009.09431 [math.ST]

  6. Crooks, G.E.: Measuring thermodynamic length. Phys. Rev. Lett. 99, 100602 (2007). https://doi.org/10.1103/PhysRevLett.99.100602

  7. Bao, D., Chern, S.-S., Shen, Z.: An Introduction to Riemann-Finsler Geometry. Graduate Texts in Mathematics, Springer, New York (2000). https://doi.org/10.1007/978-1-4612-1268-3

    Book  MATH  Google Scholar 

  8. Efron, B., Hastie, T.: Computer Age Statistical Inference, Institute of Mathematical Statistics (IMS) Monographs, vol. 5. Cambridge University Press, New York (2016). https://doi.org/10.1017/CBO9781316576533

  9. França, G., Jordan, M.I., Vidal, R.: On dissipative symplectic integration with applications to gradient-based optimization. arXiv:2004.06840 [math.OC]

  10. Gibilisco, P., Pistone, G.: Connections on non-parametric statistical manifolds by Orlicz space geometry. IDAQP 1(2), 325–347 (1998)

    MathSciNet  MATH  Google Scholar 

  11. Grabowska, K., Grabowski, J., Kuś, M., Marmo, G.: Lie groupoids in information geometry. J. Phys. A Math. Theor. 52(50), 505202 (2019). https://doi.org/10.1088/1751-8121/ab542e

  12. Ingarden, R.S.: Information geometry of thermodynamics. In: Višek, J.Á. (ed.) Transactions of the Tenth Prague Conference: Information Theory, Statistical Decision Functions, Random Processes held at Prague, vol. A, pp. 421–428. Springer, Dordrecht (1988). https://doi.org/10.1007/978-94-009-3859-5_44

    Chapter  Google Scholar 

  13. Kolmogorov, A.: Sur la notion de la moyenne. Atti. R. Accad. Naz. Lincei 12, 388 (1930)

    MATH  Google Scholar 

  14. Nagumo, M.: Über eine klasse der mittelwerte. Japan. J. Math. Trans. Abstracts 7, 71–79 (1930)

    Article  Google Scholar 

  15. Pistone, G.: Nonparametric information geometry. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2013. LNCS, vol. 8085, pp. 5–36. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40020-9_3

    Chapter  MATH  Google Scholar 

  16. Pistone, G.: Lagrangian function on the finite state space statistical bundle. Entropy 20(2), 139 (2018). https://doi.org/10.3390/e20020139

  17. Pistone, G.: Information geometry of the probability simplex. A short course. Nonlinear Phenomena Compl. Syst. 23(2), 221–242 (2020)

    Google Scholar 

  18. Rényi, A.: On measures of entropy and information. In: Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability: Contributions to the Theory of Statistics, vol. 1, pp. 547–561. University of California Press (1961)

    Google Scholar 

  19. Chirco, G.: In preparation

    Google Scholar 

Download references

Acknowledgements

The author would like to thank G. Pistone and the anonymous referees for the careful read of the manuscript and the interesting points raised.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Goffredo Chirco .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chirco, G. (2021). Rényi Relative Entropy from Homogeneous Kullback-Leibler Divergence Lagrangian. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2021. Lecture Notes in Computer Science(), vol 12829. Springer, Cham. https://doi.org/10.1007/978-3-030-80209-7_80

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-80209-7_80

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-80208-0

  • Online ISBN: 978-3-030-80209-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics