This site uses cookies. By continuing to use this site you agree to our use of cookies. To find out more, see our
Privacy and Cookies policy.
Matteo Marsili et al J. Stat. Mech. (2013) P09003 doi:10.1088/1742-5468/2013/09/P09003
Matteo Marsili1, Iacopo Mastromatteo2 and Yasser Roudi3,4
Show affiliationsThe study of complex systems is limited by the fact that only a few variables are accessible for modeling and sampling, which are not necessarily the most relevant ones to explain the system behavior. In addition, empirical data typically undersample the space of possible states. We study a generic framework where a complex system is seen as a system of many interacting degrees of freedom, which are known only in part, that optimize a given function. We show that the underlying distribution with respect to the known variables has the Boltzmann form, with a temperature that depends on the number of unknown variables. In particular, when the influence of the unknown degrees of freedom on the known variables is not too irregular, the temperature decreases as the number of variables increases. This suggests that models can be predictable only when the number of relevant variables is less than a critical threshold. Concerning sampling, we argue that the information that a sample contains on the behavior of the system is quantified by the entropy of the frequency with which different states occur. This allows us to characterize the properties of maximally informative samples: within a simple approximation, the most informative frequency size distributions have power law behavior and Zipf's law emerges at the crossover between the under sampled regime and the regime where the sample contains enough statistics to make inferences on the behavior of the system. These ideas are illustrated in some applications, showing that they can be used to identify relevant variables or to select the most informative representations of data, e.g. in data clustering.
E-print Number: 1301.3622
Cited: by |
Refers: to
Issue 09 (September 2013)
Received 18 April 2013, accepted for publication 3 August 2013
Published 6 September 2013
Matteo Marsili et al J. Stat. Mech. (2013) P09003
