Multivariate information transmission

By William J. McGill. 1954

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

Learning to Explain With Complemental Examples (2018, methodology): “theoretical viewpoint, that is, interaction-information [20] maximization.”
Theory and Evaluation Metrics for Learning Disentangled Representations (2019, background): “Separability and Independence Two representations z i , z j are separable w.r.t. the data x if they do not share common information about x , which can be formulated as follows: where I ( x, z i , z j ) denotes the multivariate mutual information [31] between x , z i and z j .”
Learning Discrete Representations via Information Maximizing Self-Augmented Training (2017, background): “;X) can be expanded as the sum of interaction information (McGill, 1954): I(Y1, . . . , YD”
Testing the significance of attribute interactions (2004, background): “While mutual information is limited to two attributes, Jakulin and Bratko (2004), following (McGill, 1954; Han, 1980), quantify an interaction among all the attributes in V, |V| = k with k-way interaction information: I(V) , − ∑ T ⊆V (−1)|V|−|T |H(T ).”
Longitudinal trends in networks of university-industry-government relations in South Korea: The role of programmatic incentives (2009, background): “McGill (1954) proposed calling this possible reduction of uncertainty “configurational information” (Jakulin & Bratko, 2004; Yeung, 2008).2 Because the information is configurational, the reduction of uncertainty cannot be attributed to one of the contributors.”
A flexible computational framework for detecting, characterizing, and interpreting statistical patterns of epistasis in genetic studies of human disease susceptibility. (2006, background): “While the concept of IG is not new (McGill, 1954), its application to the study of attribute interactions has been the focus of several recent studies (Jakulin and Bratko, 2003; Jakulin et al.”
A review of feature selection methods based on mutual information (2013, background): “Multi-information is an interesting extension of MI, proposed by McGill [42], which allows measuring the interaction among more than two variables.”
A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula (2016, background): “The resulting value quantifies the redundancy and is equal to the negative II [McGill, 1954].”
Multimodal Representation Learning via Maximization of Local Mutual Information (2021, background): “where I(z, z (1), z R (2)) is an interaction information between the three variables [21].”
Quantifying unique information (2013, background): “It has been known for a long time that a positive co-information is a sign of redundancy, while a negative co-information expresses synergy [1].”
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].”
Absolute identification by relative judgment. (2005, methodology): “Miller (1956) began with a motivation for using this measure.”
Measuring the knowledge base of an economy in terms of triple-helix relations among 'technology, organization, and territory' (2004, background): “tional source or sink of information. A 4 The so-called interaction or configurational formatio n is d efi d by these authors as the mutual informatio in three dimensions, but with the opposite sign (McGill, 1954; Han, 1980). 9 configurational reduction of the uncertainty locally counteracts the pre”
Analyzing Attribute Dependencies (2003, background): “it to 3-way interactions by introducing the interaction gain [1] or interaction information [2]:”