Monotone measures of statistical complexity
{\L}ukasz Rudnicki, Irene V. Toranzo, Pablo Sanchez-Moreno, Jesus S., Dehesa
TL;DR
This paper investigates the property of monotonicity in statistical complexity measures, comparing classical measures like Cramer-Rao, Fisher-Shannon, and LMC, inspired by quantum entanglement resource theory.
Contribution
It introduces the concept of monotonicity for complexity measures and evaluates whether key classical measures satisfy this property.
Findings
Analyzes monotonicity in classical complexity measures
Finds which measures adhere to the monotonicity property
Provides insights into the structure of complexity measures
Abstract
We introduce and discuss the notion of monotonicity for the complexity measures of general probability distributions, patterned after the resource theory of quantum entanglement. Then, we explore whether this property is satisfied by the three main intrinsic measures of complexity (Cramer-Rao, Fisher-Shannon, LMC) and some of their generalizations.
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.