Entropic Inference

Abstract

In this tutorial we review the essential arguments behing entropic inference. We focus on the epistemological notion of information and its relation to the Bayesian beliefs of rational agents. The problem of updating from a prior to a posterior probability distribution is tackled through an eliminative induction process that singles out the logarithmic relative entropy as the unique tool for inference. The resulting method of Maximum relative Entropy (ME), includes as special cases both MaxEnt and Bayes' rule, and therefore unifies the two themes of these workshops -- the Maximum Entropy and the Bayesian methods -- into a single general inference scheme.

Presented at MaxEnt 2010, the 30th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering (July 4-9, 2010, Chamonix, France)

References in corpus (2)

• Updating Probabilities
• Maximum entropy, fluctuations and priors

Cited by in corpus (13)

• Estimating the number of available states for normal and tumor tissues in gene expression space
• Entropic Mechanics: towards a stochastic description of quantum mechanics
• Axiomatic Information Thermodynamics
• On Entropy Regularized Path Integral Control for Trajectory Optimization
• Data-driven quantification of robustness and sensitivity of cell signaling networks
• Entropic Dynamics of Exchange Rates and Options
• A Deep Generative Model for Five-Class Sleep Staging with Arbitrary Sensor Input
• The Design of Global Correlation Quantifiers and Continuous Notions of Statistical Sufficiency
• Entropic Dynamics of Stocks and European Options
• Inferring transition rates on networks with incomplete knowledge
• The Census and the Second Law: An Entropic Approach to Optimal Apportionment for the U.S. House of Representatives
• Approximating the entire spectrum of nonequilibrium steady state distributions using relative entropy: An application to thermal conduction
• Falsifiability of Isolated Spacetime Regions