Criticality of mostly informative samples: a Bayesian model selection approach

DOI10.1088/1742-5468/2015/10/P10013MaRDI QIDQ3302121zbMATH OpenFDO

Authors Ariel Haimovici, Matteo Marsili

Publication date 11 August 2020

Published in Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1502.00356

Mathematics Subject Classification ID

Bayesian inference (62F15)

Abstract: We discuss a Bayesian model selection approach to high dimensional data in the deep under sampling regime. The data is based on a representation of the possible discrete states $s$, as defined by the observer, and it consists of $M$ observations of the state. This approach shows that, for a given sample size $M$, not all states observed in the sample can be distinguished. Rather, only a partition of the sampled states $s$ can be resolved. Such partition defines an {em emergent} classification $q_s$ of the states that becomes finer and finer as the sample size increases, through a process of {em symmetry breaking} between states. This allows us to distinguish between the $resolution$ of a given representation of the observer defined states $s$, which is given by the entropy of $s$, and its $relevance$ which is defined by the entropy of the partition $q_s$. Relevance has a non-monotonic dependence on resolution, for a given sample size. In addition, we characterise most relevant samples and we show that they exhibit power law frequency distributions, generally taken as signatures of "criticality". This suggests that "criticality" reflects the relevance of a given representation of the states of a complex system, and does not necessarily require a specific mechanism of self-organisation to a critical point.

Recommendations

• Statistical criticality arises in most informative representations
• On sampling and modeling complex systems
• Publication:4714291
• Bayesian feature selection with strongly regularizing priors maps to the Ising model
• Resolution and relevance trade-offs in deep learning

Cites work

• scientific article; zbMATH DE number 107482 (Why is no real title available?)
• scientific article; zbMATH DE number 1059167 (Why is no real title available?)
• Algorithms of maximum likelihood data clustering with applications
• Are biological systems poised at criticality?
• Dissecting financial markets: sectors and states
• On sampling and modeling complex systems
• Power-law distributions in empirical data
• THE POPULATION FREQUENCIES OF SPECIES AND THE ESTIMATION OF POPULATION PARAMETERS
• Zipf's Law for Cities: An Explanation

Cited in

(7)

• On sampling and modeling complex systems
• Statistical criticality arises in most informative representations
• A new spin on color quantization
• Dependence of Bayesian model selection criteria and Fisher information matrix on sample size
• Maximal relevance and optimal learning machines
• Multiscale relevance and informative encoding in neuronal spike trains
• Resolution and relevance trade-offs in deep learning

Describes a project that uses

Uses Software

• plfit

This page was built for publication: Criticality of mostly informative samples: a Bayesian model selection approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3302121)