TY - GEN
T1 - Illum information
AU - Raman, Ravi Kiran
AU - Yu, Haizi
AU - Varshney, Lav R.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/30
Y1 - 2017/8/30
N2 - Shannon's mutual information measures the degree of mutual dependence between two random variables. Two related information functionals have also been developed in the literature: Multiinformation, a multivariate extension of mutual information; and lautum information, the Csiszár conjugate of mutual information. In this work, we define illum information, the multivariate extension of lautum information and the Csiszár conjugate of multiinformation. We provide operational interpretations of this functional, including in the problem of independence testing of a set of random variables. Further, we also provide informational characterizations of illum information such as the data processing inequality and the chain rule for distributions on tree-structured graphical models. Finally, as illustrative examples, we compute the illum information for Ising models and Gauss-Markov random fields.
AB - Shannon's mutual information measures the degree of mutual dependence between two random variables. Two related information functionals have also been developed in the literature: Multiinformation, a multivariate extension of mutual information; and lautum information, the Csiszár conjugate of mutual information. In this work, we define illum information, the multivariate extension of lautum information and the Csiszár conjugate of multiinformation. We provide operational interpretations of this functional, including in the problem of independence testing of a set of random variables. Further, we also provide informational characterizations of illum information such as the data processing inequality and the chain rule for distributions on tree-structured graphical models. Finally, as illustrative examples, we compute the illum information for Ising models and Gauss-Markov random fields.
UR - http://www.scopus.com/inward/record.url?scp=85031003788&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85031003788&partnerID=8YFLogxK
U2 - 10.1109/ITA.2017.8023479
DO - 10.1109/ITA.2017.8023479
M3 - Conference contribution
AN - SCOPUS:85031003788
T3 - 2017 Information Theory and Applications Workshop, ITA 2017
BT - 2017 Information Theory and Applications Workshop, ITA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 Information Theory and Applications Workshop, ITA 2017
Y2 - 12 February 2017 through 17 February 2017
ER -