An operational information decomposition via synergistic disclosure
作者： Fernando E Rosas , Pedro A M Mediano , Borzoo Rassouli , Adam B Barrett
关键词: Complex system 、 Computer science 、 Decomposition (computer science) 、 Data science 、 Interpretation (logic) 、 Information privacy 、 Range (mathematics)
摘要: Multivariate information decompositions hold promise to yield insight into complex systems, and stand out for their ability identify synergistic phenomena. However, the adoption of these approaches has been hindered by there being multiple possible decompositions, no precise guidance preferring one over others. At heart this disagreement lies absence a clear operational interpretation what is. Here we fill gap proposing new decomposition based on novel operationalisation informational synergy, which leverages recent developments in literature data privacy. Our is defined any number sources, its atoms can be calculated using elementary optimisation techniques. The provides natural coarse-graining that scales gracefully with system's size, applicable wide range scenarios practical interest.
arxiv.org
sci-hub.st 参考文章(51)
Virgil Griffith, Christof Koch, Quantifying Synergistic Mutual Information arXiv: Information Theory. pp. 159- 190 ,(2014) , 10.1007/978-3-642-53734-9_6
Adam B. Barrett, Exploration of synergistic and redundant information sharing in static and dynamical Gaussian systems Physical Review E. ,vol. 91, pp. 052802- ,(2015) , 10.1103/PHYSREVE.91.052802
Randall D. Beer, Paul L. Williams, Nonnegative Decomposition of Multivariate Information arXiv: Information Theory. ,(2010)
Tiancheng Li, Ninghui Li, On the tradeoff between privacy and utility in data publishing Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09. pp. 517- 526 ,(2009) , 10.1145/1557019.1557079
CE Shennon, Warren Weaver, A mathematical theory of communication Bell System Technical Journal. ,vol. 27, pp. 379- 423 ,(1948) , 10.1002/J.1538-7305.1948.TB01338.X
M. Mitchell Waldrop, Complexity: The Emerging Science at the Edge of Order and Chaos ,(1992)
Malte Harder, Christoph Salge, Daniel Polani, Bivariate measure of redundant information. Physical Review E. ,vol. 87, pp. 012130- ,(2013) , 10.1103/PHYSREVE.87.012130
V. Varadan, D. M. Miller, D. Anastassiou, Computational inference of the molecular logic for synaptic connectivity in C. elegans Bioinformatics. ,vol. 22, pp. 497- 506 ,(2006) , 10.1093/BIOINFORMATICS/BTL224
Bin Yang, Issei Sato, Hiroshi Nakagawa, Bayesian Differential Privacy on Correlated Data international conference on management of data. pp. 747- 762 ,(2015) , 10.1145/2723372.2747643
E. Ganmor, R. Segev, E. Schneidman, Sparse low-order interaction network underlies a highly correlated and learnable neural population code Proceedings of the National Academy of Sciences of the United States of America. ,vol. 108, pp. 9679- 9684 ,(2011) , 10.1073/PNAS.1019641108