Generalizing Information to the Evolution of Rational Belief
Abstract
Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome’s plausibility. Information measures based on Shannon’s concept of entropy include realization information, Kullback–Leibler divergence, Lindley’s information in experiment, cross entropy, and mutual information. We derive a general theory of information from first principles that accounts for evolving belief and recovers all of these measures. Rather than simply gauging uncertainty, information is understood in this theory to measure change in belief. We may then regard entropy as the information we expect to gain upon realization of a discrete latent random variable. This theory of information is compatible with the Bayesian paradigm in which rational belief is updated as evidence becomes available. Furthermore, this theory admits novel measures of information with well-defined properties, which we explored in both analysis and experiment. This view of information illuminates the study of machine learning by allowing us to quantify information captured by a predictive model and distinguish it from residual information contained in training data. We gain related insights regarding feature selection, anomaly detection, and novel Bayesian approaches.
- Authors:
-
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-CA), Livermore, CA (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1605735
- Alternate Identifier(s):
- OSTI ID: 1618088
- Report Number(s):
- SAND-2020-3103J; SAND-2019-13298J
Journal ID: ISSN 1099-4300; ENTRFG; 684733
- Grant/Contract Number:
- AC04-94AL85000
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Entropy
- Additional Journal Information:
- Journal Volume: 22; Journal Issue: 1; Journal ID: ISSN 1099-4300
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; information; Bayesian inference; entropy; self information; mutual information; Kullback–Leibler divergence; Lindley information; maximal uncertainty; proper utility
Citation Formats
Duersch, Jed A., and Catanach, Thomas A. Generalizing Information to the Evolution of Rational Belief. United States: N. p., 2020.
Web. doi:10.3390/e22010108.
Duersch, Jed A., & Catanach, Thomas A. Generalizing Information to the Evolution of Rational Belief. United States. https://doi.org/10.3390/e22010108
Duersch, Jed A., and Catanach, Thomas A. Thu .
"Generalizing Information to the Evolution of Rational Belief". United States. https://doi.org/10.3390/e22010108. https://www.osti.gov/servlets/purl/1605735.
@article{osti_1605735,
title = {Generalizing Information to the Evolution of Rational Belief},
author = {Duersch, Jed A. and Catanach, Thomas A.},
abstractNote = {Information theory provides a mathematical foundation to measure uncertainty in belief. Belief is represented by a probability distribution that captures our understanding of an outcome’s plausibility. Information measures based on Shannon’s concept of entropy include realization information, Kullback–Leibler divergence, Lindley’s information in experiment, cross entropy, and mutual information. We derive a general theory of information from first principles that accounts for evolving belief and recovers all of these measures. Rather than simply gauging uncertainty, information is understood in this theory to measure change in belief. We may then regard entropy as the information we expect to gain upon realization of a discrete latent random variable. This theory of information is compatible with the Bayesian paradigm in which rational belief is updated as evidence becomes available. Furthermore, this theory admits novel measures of information with well-defined properties, which we explored in both analysis and experiment. This view of information illuminates the study of machine learning by allowing us to quantify information captured by a predictive model and distinguish it from residual information contained in training data. We gain related insights regarding feature selection, anomaly detection, and novel Bayesian approaches.},
doi = {10.3390/e22010108},
journal = {Entropy},
number = 1,
volume = 22,
place = {United States},
year = {Thu Jan 16 00:00:00 EST 2020},
month = {Thu Jan 16 00:00:00 EST 2020}
}
Web of Science
Works referenced in this record:
A Mathematical Theory of Communication
journal, July 1948
- Shannon, C. E.
- Bell System Technical Journal, Vol. 27, Issue 3
Estimating the Dimension of a Model
journal, March 1978
- Schwarz, Gideon
- The Annals of Statistics, Vol. 6, Issue 2
The Theory of Information
journal, January 1951
- Barnard, G. A.
- Journal of the Royal Statistical Society: Series B (Methodological), Vol. 13, Issue 1
On rational betting systems
journal, March 1962
- Adams, Ernest W.
- Archiv für Mathematische Logik und Grundlagenforschung, Vol. 6, Issue 1-2
A comprehensive classification of complex statistical systems and an axiomatic derivation of their entropy and distribution functions
journal, January 2011
- Hanel, R.; Thurner, S.
- EPL (Europhysics Letters), Vol. 93, Issue 2
On confirmation and rational betting
journal, September 1955
- Lehman, R. Sherman
- Journal of Symbolic Logic, Vol. 20, Issue 3
On the Distribution Function of Additive Functions
journal, January 1946
- Erdos, P.
- The Annals of Mathematics, Vol. 47, Issue 1
Kullback-Leibler information as a basis for strong inference in ecological studies
journal, January 2001
- Burnham, Kenneth P.; Anderson, David R.
- Wildlife Research, Vol. 28, Issue 2
Information Theory and Statistical Mechanics
journal, May 1957
- Jaynes, E. T.
- Physical Review, Vol. 106, Issue 4
Maximum Entropy for Hypothesis Formulation, Especially for Multidimensional Contingency Tables
journal, September 1963
- Good, I. J.
- The Annals of Mathematical Statistics, Vol. 34, Issue 3
Group entropies, correlation laws, and zeta functions
journal, August 2011
- Tempesta, Piergiulio
- Physical Review E, Vol. 84, Issue 2
A new look at the statistical model identification
journal, December 1974
- Akaike, H.
- IEEE Transactions on Automatic Control, Vol. 19, Issue 6
Generalized Shannon–Khinchin axioms and uniqueness theorem for pseudo-additive entropies
journal, October 2014
- Ilić, Velimir M.; Stanković, Miomir S.
- Physica A: Statistical Mechanics and its Applications, Vol. 411
On Information and Sufficiency
journal, March 1951
- Kullback, S.; Leibler, R. A.
- The Annals of Mathematical Statistics, Vol. 22, Issue 1
Properties of cross-entropy minimization
journal, July 1981
- Shore, J.; Johnson, R.
- IEEE Transactions on Information Theory, Vol. 27, Issue 4
On a Measure of the Information Provided by an Experiment
journal, December 1956
- Lindley, D. V.
- The Annals of Mathematical Statistics, Vol. 27, Issue 4
Understanding predictive information criteria for Bayesian models
journal, August 2013
- Gelman, Andrew; Hwang, Jessica; Vehtari, Aki
- Statistics and Computing, Vol. 24, Issue 6
Probability, Frequency and Reasonable Expectation
journal, January 1946
- Cox, R. T.
- American Journal of Physics, Vol. 14, Issue 1
Principal Information Theoretic Approaches
journal, December 2000
- Soofi, Ehsan S.
- Journal of the American Statistical Association, Vol. 95, Issue 452
Generalized statistics: yet another generalization
journal, September 2004
- Jizba, Petr; Arimitsu, Toshihico
- Physica A: Statistical Mechanics and its Applications, Vol. 340, Issue 1-3
Expected Information as Expected Utility
journal, May 1979
- Bernardo, Jose M.
- The Annals of Statistics, Vol. 7, Issue 3
Bayes' Method for Bookies
journal, August 1969
- Freedman, David A.; Purves, Roger A.
- The Annals of Mathematical Statistics, Vol. 40, Issue 4
Dynamic Coherence and Probability Kinematics
journal, March 1987
- Skyrms, Brian
- Philosophy of Science, Vol. 54, Issue 1
Information Measures in Perspective: Information Measures in Perspective
journal, December 2010
- Ebrahimi, Nader; Soofi, Ehsan S.; Soyer, Refik
- International Statistical Review, Vol. 78, Issue 3
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
Capturing the Intangible Concept of Information
journal, December 1994
- Soofi, Ehsan S.
- Journal of the American Statistical Association, Vol. 89, Issue 428
Sur une généralisation des intégrales de M. J. Radon
journal, January 1930
- Nikodym, Otton
- Fundamenta Mathematicae, Vol. 15
Axiomatic derivation of the principle of maximum entropy and the principle of minimum cross-entropy
journal, January 1980
- Shore, J.; Johnson, R.
- IEEE Transactions on Information Theory, Vol. 26, Issue 1
On rational betting systems
journal, April 1964
- Adams, Ernest W.
- Archiv für Mathematische Logik und Grundlagenforschung, Vol. 6, Issue 3-4
Friendship stability in adolescence is associated with ventral striatum responses to vicarious rewards
journal, January 2021
- Schreuders, Elisabeth; Braams, Barbara R.; Crone, Eveline A.
- Nature Communications, Vol. 12, Issue 1
Skillful statistical models to predict seasonal wind speed and solar radiation in a Yangtze River estuary case study
journal, May 2020
- Zeng, Peng; Sun, Xun; Farnham, David J.
- Scientific Reports, Vol. 10, Issue 1
A Mathematical Theory of Communication
journal, October 1948
- Shannon, C. E.
- Bell System Technical Journal, Vol. 27, Issue 4
Understanding predictive information criteria for Bayesian models
preprint, January 2013
- Gelman, Andrew; Hwang, Jessica; Vehtari, Aki
- arXiv
Generalized Shannon-Khinchin Axioms and Uniqueness Theorem for Pseudo-additive Entropies
text, January 2013
- Ilic, Velimir M.; Stankovic, Miomir S.
- arXiv
Maximum Entropy Principle in statistical inference: case for non-Shannonian entropies
text, January 2018
- Jizba, Petr; Korbel, Jan
- arXiv
Generalized statistics: yet another generalization
text, January 2003
- Jizba, Petr; Arimitsu, Toshihico
- arXiv
Principal Information Theoretic Approaches
journal, December 2000
- Soofi, Ehsan S.
- Journal of the American Statistical Association, Vol. 95, Issue 452
Information Properties of Order Statistics and Spacings
journal, January 2004
- Ebrahimi, N.; Soofi, E. S.; Zahedi, H.
- IEEE Transactions on Information Theory, Vol. 50, Issue 1
On a Measure of the Information Provided by an Experiment
journal, December 1956
- Lindley, D. V.
- The Annals of Mathematical Statistics, Vol. 27, Issue 4
On the Distribution Function of Additive Functions
journal, January 1946
- Erdos, P.
- The Annals of Mathematics, Vol. 47, Issue 1
Sur une généralisation des intégrales de M. J. Radon
journal, January 1930
- Nikodym, Otton
- Fundamenta Mathematicae, Vol. 15
Works referencing / citing this record:
Bayesian inference of Stochastic reaction networks using Multifidelity Sequential Tempered Markov Chain Monte Carlo
preprint, January 2020
- Catanach, Thomas A.; Vo, Huy D.; Munsky, Brian
- arXiv