Estimators, escort probabilities, and phi-exponential families in statistical physics
Jan Naudts

TL;DR
This paper generalizes the Cramer-Rao lower bound to pairs of probability distribution families, introducing phi-exponential families and exploring their dual structure, with implications for statistical physics.
Contribution
It introduces phi-exponential families and extends the Cramer-Rao bound to escort probability pairs, revealing their dual structure.
Findings
Generalized Cramer-Rao bound for escort families
Identification of optimal phi-exponential families
Analysis of dual structure in statistical physics
Abstract
The lower bound of Cramer and Rao is generalized to pairs of families of probability distributions, one of which is escort to the other. This bound is optimal for certain families, called phi-exponential in the paper. Their dual structure is explored.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStatistical Mechanics and Entropy · Advanced Statistical Methods and Models · Bayesian Methods and Mixture Models
