THE CO-INFORMATION LATTICE

By Anthony J. Bell. 2003

277 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Theory and Evaluation Metrics for Learning Disentangled Representations (2019, background): “The meaning of a negative I ( x, z i , z j ) remains elusive [4].”
A review of feature selection methods based on mutual information (2013, background): “iﬃcult interpretation, e.g. the multi-information can take negative values, among other reasons. However, there are some interesting papers about the interaction among variables that use this concept [42, 68, 30, 5]. The multi-information can be understood as the amount of information common to all ”
Interaction information for causal inference: The case of directed triangle (2017, background): “The general formula for interaction information for a set of variables V is defined as [6]”
SGD on Neural Networks Learns Functions of Increasing Complexity (2019, background): “(4)The quantity μY (F,L) can also be thought as a multivariate generalization of mutual information [28, 7].”
On Measures of Entropy and Information (2015, background): “Total correlation (multivariate constraint, multi-information, integration, redundancy) [9, 13, 14, 10] Quanti(cid:224)es the total correlation or redundancy between a set of variables.”
Joint Blind Source Separation by Multi-set Canonical Correlation Analysis (2009, methodology): “Motivated by the multivariate generalization of mutual information , in [29], dependence among multiple random variables is described by a graph structure and the separation of the dependent components is posed as a density estimation problem to form the method of dependent component analysis (DCA).”