Mostrar el registro sencillo del ítem
dc.contributor.author
Haimovici, Ariel
dc.contributor.author
Marsili, Matteo
dc.date.available
2018-09-13T18:06:57Z
dc.date.issued
2015-10
dc.identifier.citation
Haimovici, Ariel; Marsili, Matteo; Criticality of mostly informative samples: A Bayesian model selection approach; IOP Publishing; Journal of Statistical Mechanics: Theory and Experiment; 2015; 10; 10-2015; 1-26; P10013
dc.identifier.issn
1742-5468
dc.identifier.uri
http://hdl.handle.net/11336/59551
dc.description.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 a partition defines an emergent classification qs of the states that becomes finer and finer as the sample size increases, through a process of 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 qs. Relevance has a nonmonotonic 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.
dc.format
application/pdf
dc.language.iso
eng
dc.publisher
IOP Publishing
dc.rights
info:eu-repo/semantics/openAccess
dc.rights.uri
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.subject
Data Mining (Theory)
dc.subject
Statistical Inference
dc.subject.classification
Astronomía
dc.subject.classification
Ciencias Físicas
dc.subject.classification
CIENCIAS NATURALES Y EXACTAS
dc.title
Criticality of mostly informative samples: A Bayesian model selection approach
dc.type
info:eu-repo/semantics/article
dc.type
info:ar-repo/semantics/artículo
dc.type
info:eu-repo/semantics/publishedVersion
dc.date.updated
2018-09-13T13:14:30Z
dc.journal.volume
2015
dc.journal.number
10
dc.journal.pagination
1-26; P10013
dc.journal.pais
Reino Unido
dc.journal.ciudad
Londres
dc.description.fil
Fil: Haimovici, Ariel. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Física; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
dc.description.fil
Fil: Marsili, Matteo. The Abdus Salam; Italia
dc.journal.title
Journal of Statistical Mechanics: Theory and Experiment
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1088/1742-5468/2015/10/P10013
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/http://iopscience.iop.org/article/10.1088/1742-5468/2015/10/P10013/meta
dc.relation.alternativeid
info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/1502.00356
Archivos asociados