On the Application of Information Geometry to the Manifold Induced by the Parameters of the Mean Square Error of Probability Functions
Argelia Aguilar Garduño, Candelaria Sansores Pérez, Antonio Neme · 2026
Read On the Application of Information Geometry to the Manifold Induced by the Parameters of the Mean Square Error of Probability Functions by Argelia Aguilar Garduño, Candelaria Sansores Pérez, Antonio Neme (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13297668.txt.
Description
Probability distributions can be compared as points on a curved surface, and Argelia Aguilar Garduño with co-authors extend that geometric view in a 2026 mathematics paper. Their route describes each distribution through the coefficients of a quadratic curve fitted to its mean square error.
Those coefficients span a manifold of their own, letting distributions from different families be compared by the arc length between their points. The authors work out the geometry of this error-based surface and set it beside the Fisher-Rao distance, the standard yardstick of information geometry. Their empirical tests suggest the error-based description can reveal relationships between distributions that conventional comparisons may miss.
Catalog record
| CREATOR | Argelia Aguilar Garduño, Candelaria Sansores Pérez, Antonio Neme |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36900 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |