Max-entropy
Max-Entropy is a principle in information theory that identifies the probability distribution with the greatest entropy among all distributions satisfying given constraints, thereby representing maximal uncertainty consistent with available information.
698
Publications
56.3K
Citations
1.1K
Authors
619
Institutions
Publications per year
2017–2026
87
Variants
Maximum Entropy
Parents
698
Information theory and statistics
Journal of the Franklin Institute · 1959 · 7.2K citations
On the rationale of maximum-entropy methods
E. T. Jaynes · Proceedings of the IEEE · 1982 · 1.7K citations
Information Theory and Statistics.
Meyer Dwass, S. Kullback · American Mathematical Monthly · 1960 · 1.5K citations
Mathematical Foundations of Information Theory.
J. Laurie Snell, Aleksandr I︠A︡kovlevich Khinchin, Ray Silverman et al. · American Mathematical Monthly · 1959 · 1.5K citations
Algorithmic Information Theory
Gregory J. Chaitin · IBM Journal of Research and Development · 1977 · 1K citations
1–5 of 698
1.1K
9
h-index
7
h-index
5
h-index
5
h-index
5
h-index
1–5 of 1.1K
619

University of Waterloo
Waterloo, Canada
14 h-index
22 publications
807 citations

Centre National de la Recherche Scientifique
Paris, France
13 h-index
22 publications
541 citations
University of Cambridge
Cambridge, United Kingdom
11 h-index
17 publications
1.7K citations
ETH Zurich
Zurich, Switzerland
11 h-index
19 publications
3.2K citations
Stanford University
Stanford, United States
9 h-index
10 publications
829 citations
University of California, Berkeley
Berkeley, United States
9 h-index
10 publications
921 citations
National University of Singapore
Singapore, Singapore
8 h-index
14 publications
1.5K citations

Polish Academy of Sciences
Warsaw, Poland
8 h-index
14 publications
621 citations
1–8 of 619
26 publications · 703 citations
17
h-index
18 publications · 2.2K citations
16
h-index
21 publications · 843 citations
15
h-index
Repository · 17 publications · 848 citations
14
h-index
12 publications · 577 citations
11
h-index
1–5