paper-with-me

홈 › Papers

Correlation Dimension of Natural Language in a Statistical Manifold

2024-05-10 · Xin Du, Kumiko Tanaka-Ishii

The correlation dimension of natural language is measured by applying the Grassberger-Procaccia algorithm to high-dimensional sequences produced by a large-scale language model. This method, previously studied only in a Euclidean space, is reformulated in a statistical manifold via the Fisher-Rao distance. Language exhibits a multifractal, with global self-similarity and a universal dimension around 6.5, which is smaller than those of simple discrete random sequences and larger than that of a Barab\'asi-Albert process. Long memory is the key to producing self-similarity. Our method is applicable to any probabilistic model of real-world discrete sequences, and we show an application to music data.

📄 PDF Abstract BibTeX arXiv:2405.06321

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Statistical exploration of the Manifold Hypothesis

2022-08-24 · Nick Whiteley, Annie Gray, Patrick Rubin-Delanchy

The Manifold Hypothesis is a widely accepted tenet of Machine Learning which asserts that nominally high-dimensional data are in fact concentrated near a low-dimensional manifold, embedded in high-dimensional space. This…

Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds

2024-08-13 · Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb

The manifold hypothesis says that natural high-dimensional data lie on or around a low-dimensional manifold. The recent success of statistical and learning-based methods in very high dimensions empirically supports this …

Characterizing Neural Manifolds' Properties and Curvatures using Normalizing Flows

2025-06-13 · Peter Bouss, Sandra Nestler, Kirsten Fischer, Claudia Merger 외

Neuronal activity is found to lie on low-dimensional manifolds embedded within the high-dimensional neuron space. Variants of principal component analysis are frequently employed to assess these manifolds. These methods …

On consistent estimation of dimension values

2024-12-18 · Alejandro Cholaquidis, Antonio Cuevas, Beatriz Pateiro-López

The problem of estimating, from a random sample of points, the dimension of a compact subset S of the Euclidean space is considered. The emphasis is put on consistency results in the statistical sense. That is, statement…

Symmetry in language statistics shapes the geometry of model representations

2026-02-16 · Dhruva Karkada, Daniel J. Korchinski, Andres Nava, Matthieu Wyart 외 arxiv

The internal representations learned by language models consistently exhibit striking geometric structure: calendar months organize into a circle, historical years form a smooth one-dimensional manifold, and cities' lati…