Advertisement

Pointless Learning

  • Florence Clerc
  • Vincent Danos
  • Fredrik Dahlqvist
  • Ilias GarnierEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10203)

Abstract

Bayesian inversion is at the heart of probabilistic programming and more generally machine learning. Understanding inversion is made difficult by the pointful (kernel-centric) point of view usually taken in the literature. We develop a pointless (kernel-free) approach to inversion. While doing so, we revisit some foundational objects of probability theory, unravel their category-theoretical underpinnings and show how pointless Bayesian inversion sits naturally at the centre of this construction.

References

  1. 1.
    Ackerman, N.L., Freer, C.E., Roy, D.M.: Noncomputable conditional distributions. In: Proceedings of the 26th Annual IEEE Symposium on Logic in Computer Science, LICS, Toronto, Ontario, Canada, pp. 107–116, 21–24 June 2011Google Scholar
  2. 2.
    Aliprantis, C., Border, K.: Infinite Dimensional Analysis, vol. 32006. Springer, Heidelberg (1999)CrossRefzbMATHGoogle Scholar
  3. 3.
    Chaput, P., Danos, V., Panangaden, P., Plotkin, G.: Approximating markov processes by averaging. J. ACM 61(1), 45 pages (2014)Google Scholar
  4. 4.
    Clerc, F., Dahlqvist, F., Danos, V., Garnier, I.: Pointless learning (long version) (2017)Google Scholar
  5. 5.
    Culbertson, J., Sturtz, K.: A categorical foundation for Bayesian probability. Appl. Categorical Struct. 22(4), 647–662 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Dahlqvist, F., Danos, V., Garnier, I., Kammar, O.: Bayesian inversion by omega-complete cone duality (invited paper). In: Desharnais, J., Jagadeesan, R. (eds.) 27th International Conference on Concurrency Theory (CONCUR 2016), vol. 59 of Leibniz International Proceedings in Informatics (LIPIcs), pp. 1:1–1:15. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany (2016)Google Scholar
  7. 7.
    Giry, M.: A categorical approach to probability theory. In: Banaschewski, B. (ed.) Categorical Aspects of Topology and Analysis. LNM, vol. 915, pp. 68–85. Springer, Heidelberg (1982). doi: 10.1007/BFb0092872 CrossRefGoogle Scholar
  8. 8.
    Kallenberg, O.: Foundations of Modern Probability. Springer, New York (1997)zbMATHGoogle Scholar
  9. 9.
    Kechris, A.S.: Classical Descriptive Set Theory. Graduate Text in Mathematics, vol. 156. Springer, New York (1995)zbMATHGoogle Scholar
  10. 10.
    Kozen, D.: A probabilistic PDL. In: Proceedings of the Fifteenth Annual ACM Symposium on Theory of Computing, STOC 1983, pp. 291–297. ACM, New York (1983)Google Scholar
  11. 11.
    Selinger, P.: Towards a semantics for higher-order quantum computation. In: Proceedings of the 2nd International Workshop on Quantum Programming Languages, TUCS General Publication, vol. 33, pp. 127–143 (2004)Google Scholar
  12. 12.
    Staton, S., Yang, H., Heunen, C., Kammar, O., Wood, F.: Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints. CoRR, abs/1601.04943 (2016)Google Scholar
  13. 13.
    Villani, C.: Optimal Transport, Old and New. Grundlehren der mathematischen Wissenschaften. Springer, Heidelberg (2006)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  • Florence Clerc
    • 1
  • Vincent Danos
    • 2
    • 4
  • Fredrik Dahlqvist
    • 3
  • Ilias Garnier
    • 4
    Email author
  1. 1.McGill UniversityMontrealCanada
  2. 2.ENS Paris/CNRSParisFrance
  3. 3.UCLLondonUK
  4. 4.University of EdinburghEdinburghScotland

Personalised recommendations