Abstract
Previous works established that entropy is characterized uniquely as the first cohomology class in a topos and described some of its applications to the unsupervised classification of gene expression modules or cell types. These studies raised important questions regarding the statistical meaning of the resulting cohomology of information and its interpretation or consequences with respect to usual data analysis and statistical physics. This paper aims to present the computational methods of information cohomology and to propose its interpretations in terms of statistical physics and machine learning. In order to further underline the cohomological nature of information functions and chain rules, the computation of the cohomology in low degrees is detailed to show more directly that the k multivariate mutual information () are -coboundaries. The -cocycles condition corresponds to , which generalizes statistical independence to arbitrary degree k. Hence, the cohomology can be interpreted as quantifying the statistical dependences and the obstruction to factorization. I develop the computationally tractable subcase of simplicial information cohomology represented by entropy and information landscapes and their respective paths, allowing investigation of Shannon’s information in the multivariate case without the assumptions of independence or of identically distributed variables. I give an interpretation of this cohomology in terms of phase transitions in a model of k-body interactions, holding both for statistical physics without mean field approximations and for data points. The components define a self-internal energy functional and components define the contribution to a free energy functional (the total correlation) of the k-body interactions. A basic mean field model is developed and computed on genetic data reproducing usual free energy landscapes with phase transition, sustaining the analogy of clustering with condensation. The set of information paths in simplicial structures is in bijection with the symmetric group and random processes, providing a trivial topological expression of the second law of thermodynamics. The local minima of free energy, related to conditional information negativity and conditional independence, characterize a minimum free energy complex. This complex formalizes the minimum free-energy principle in topology, provides a definition of a complex system and characterizes a multiplicity of local minima that quantifies the diversity observed in biology. I give an interpretation of this complex in terms of unsupervised deep learning where the neural network architecture is given by the chain complex and conclude by discussing future supervised applications.
Highlights
The present paper aims to provide a comprehensive introduction and interpretation in terms of statistics, statistical physics and machine learning of the information cohomology theory developed in References [1,2]
Just as topos have been used as a communication bridge allowing the translation of theorems between different domains and to unify mathematical theories [5], information cohomology can help in further unraveling some equivalences between different disciplines and shall play a foundational role in both as already proposed by Doering and Isham considering only probability structures [6,7]
Following all the work of these past decades on the application of statistical physics to biological systems, we propose that the epigenetic process implements the first two laws of thermodynamics, weak topological versions of which are proposed to hold in the raw data space
Summary
The present paper aims to provide a comprehensive introduction and interpretation in terms of statistics, statistical physics and machine learning of the information cohomology theory developed in References [1,2]. It presents the computational aspects of the application of information cohomology to data presented in Reference [3] and in the associated paper [2], which consists of an unsupervised classification of cell types or gene modules and provides a generic model for epigenetic co-regulation and differentiation. It appears that knowledge is a form of energy [17] and the results suggest that there are important resources of such information-energy in the k-body dependences even beyond pairwise interactions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have