Abstract
A longstanding open problem in statistics is finding an explicit expression for the probability measure which maximizes entropy with respect to given constraints. In this paper a solution to this problem is found, using perturbative Feynman calculus. The explicit expression is given as a sum over weighted trees.
Similar content being viewed by others
Notes
See for example the proof in Joel Feldman’s lecture notes, http://www.math.ubc.ca/~feldman/m425/impFnThm.pdf. To apply the argument we need that \((\partial f)(x,y) \in \textit{Hom}(V,V^*)\) is invertible for all \((x,y) \in U \times W\). Since \(\partial f = B({\text {id}} - \partial g)\) this follows from our assumption that \((\partial g)(x,y) \in \textit{Hom}(V,V)\) is contracting.
References
Avellaneda, M., Friedman, C., Holmes, R., Samperi, D.: Calibrating volatility surfaces via relative-entropy minimization. App. Math. Financ. 4(1), 37–64 (1997)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley, New York (2012)
Etingof, P.: Geometry and quantum field theory. MIT OpenCourseware 18.238 (2002)
Frisch, H.L., Lebowitz, J.L.: The Equilibrium Theory of Classical Fluids. Benjamin, New York (1964)
Jaynes, E.T.: Information theory and statistical mechanics. Phys. Rev. 106(4), 620–630 (1957)
Jaynes, E.T.: Information theory and statistical mechanics. II. Phys. Rev. 108(2), 171–190 (1957)
Lin, H.W., Tegmark, M., Rolnick. D.: Why does deep and cheap learning work so well? arXiv preprint. arXiv:1608.08225 (2016)
Shell, S.M.: The relative entropy is fundamental to multiscale and inverse thermodynamic problems. J. Chem. Phys. 129(14), 144108 (2008)
Acknowledgements
We thank O. Bozo, B. Gomberg, R.S. Melzer, A. Moscovitch-Eiger, R. Schweiger, A. Solomon and D. Zernik for discussions related to the work presented here. R.T. was partially supported by Dr. Max Rössler, the Walter Haefner Foundation and the ETH Zurich Foundation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Appendix A: Proof of Lemma 3
Appendix A: Proof of Lemma 3
Recall that by Lemma 24
Hence \(\lambda _{0}\) is an analytic function of \(\lambda _{1},\ldots ,\lambda _{k}\) around \(\lambda _{1}=\dots =\lambda _{k}=0\). Now,
So that \(\rho _{i}(\lambda _{1},\ldots ,\lambda _{k})\) is an analytic function of \(\lambda _{1},\ldots ,\lambda _{k}\)
The proof that \(\lambda _{i}=\lambda _{i}(\rho _{1},\ldots ,\rho _{k})\) is an analytic function of \(\rho _{1},\ldots ,\rho _{k}\) around
uses the analytic inverse function theorem. It is enough to show that the Jacobian \(\frac{\partial (\rho _{1},\ldots ,\rho _{k})}{\partial (\lambda _{1},\ldots ,\lambda _{k})}\) is invertible for\(\lambda _{1}=\dots =\lambda _{k}=0.\)
But
Evaluation at \(\lambda _{1}=\dots =\lambda _{k}=0\) gives
By assumption the KL constraint problem is normalized, hence
The Jacobian \(\frac{\partial (\rho _{1},\ldots ,\rho _{k})}{\partial (\lambda _{1},\ldots ,\lambda _{k})}=I_{k}\) is thus invertible. \(\square \)
Rights and permissions
About this article
Cite this article
Netser Zernik, A., Schlank, T.M. & Tessler, R.J. Exact Maximum-Entropy Estimation with Feynman Diagrams. J Stat Phys 170, 731–747 (2018). https://doi.org/10.1007/s10955-018-1960-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10955-018-1960-x