Table of Contents
Fetching ...

Quantization of Ricci Curvature in Information Geometry

Carlos C. Rodriguez

TL;DR

This paper proves the conjecture that the volume-averaged Ricci scalarcomputed with respect to the Fisher information metric is universally quantized to positive half-integers via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples.

Abstract

In 2004, while studying the information geometry of binary Bayesian networks (bitnets), the author conjectured that the volume-averaged Ricci scalar <R> computed with respect to the Fisher information metric is universally quantized to positive half-integers: <R> in (1/2)Z. This paper resolves the conjecture after 20 years. We prove it for tree-structured and complete-graph bitnets via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples. We extend the program to Gaussian DAG networks, where a sign dichotomy holds: discrete bitnets have positive curvature, while Gaussian networks form solvable Lie groups with negative curvature.

Quantization of Ricci Curvature in Information Geometry

TL;DR

This paper proves the conjecture that the volume-averaged Ricci scalarcomputed with respect to the Fisher information metric is universally quantized to positive half-integers via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples.

Abstract

In 2004, while studying the information geometry of binary Bayesian networks (bitnets), the author conjectured that the volume-averaged Ricci scalar <R> computed with respect to the Fisher information metric is universally quantized to positive half-integers: <R> in (1/2)Z. This paper resolves the conjecture after 20 years. We prove it for tree-structured and complete-graph bitnets via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples. We extend the program to Gaussian DAG networks, where a sign dichotomy holds: discrete bitnets have positive curvature, while Gaussian networks form solvable Lie groups with negative curvature.
Paper Structure (34 sections, 16 theorems, 27 equations, 3 tables)

This paper contains 34 sections, 16 theorems, 27 equations, 3 tables.

Key Result

Theorem 1.2

The directed line $\tilde{L}_n$ and the exploding star $\tilde{E}_n$ (one parent, $n-1$ children) have identical Fisher information volumes and identical volume-averaged Ricci scalars:

Theorems & Definitions (39)

  • Conjecture 1.1: Rodríguez, 2004
  • Theorem 1.2: Equal volumes and equal curvatures
  • proof
  • Remark 1.3: Error in 2004
  • Theorem 3.1: Complete DAGs
  • Theorem 3.2: Equal volumes and curvatures
  • Remark 3.3: Interpretation
  • Theorem 3.4: Ricci scalar of $\tilde{C}_{n+1}$
  • Theorem 3.5: Curvature sign inversion
  • proof
  • ...and 29 more