English
Related papers

Related papers: The Information-Geometric Perspective of Compositi…

200 papers

The enduring legacy of Euclidean geometry underpins classical machine learning, which, for decades, has been primarily developed for data lying in Euclidean space. Yet, modern machine learning increasingly encounters richly structured data…

The fundamental equations of various disciplines often seem to share the same basic structure. Natural selection increases information in the same way that Bayesian updating increases information. Thermodynamics and the forms of common…

Populations and Evolution · Quantitative Biology 2018-12-18 Steven A. Frank

Supervised dimensionality reduction maps labeled data into a low-dimensional feature space while preserving class discriminability. A common approach is to maximize a statistical measure of dissimilarity between classes in the feature…

Machine Learning · Statistics 2025-11-03 Daniel Herrera-Esposito , Johannes Burge

One considers geometry with the intransitive equaivalence relation. Such a geometry is a physical geometry, i.e. it is described completely by the world function, which is a half of the squared distance function. The physical geometry…

General Mathematics · Mathematics 2009-03-30 Yuri A. Rylov

It is shown that for any ensemble, whether classical or quantum, continuous or discrete, there is only one measure of the "volume" of the ensemble that is compatible with several basic geometric postulates. This volume measure is thus a…

Data Analysis, Statistics and Probability · Physics 2009-10-31 Michael J. W. Hall

Principal Component Analysis (PCA) is a workhorse of modern data science. While PCA assumes the data conforms to Euclidean geometry, for specific data types, such as hierarchical and cyclic data structures, other spaces are more…

Machine Learning · Statistics 2024-07-11 Puoya Tabaghi , Michael Khanzadeh , Yusu Wang , Sivash Mirarab

Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact…

Machine Learning · Statistics 2020-08-13 Nutan Chen , Alexej Klushyn , Francesco Ferroni , Justin Bayer , Patrick van der Smagt

A central issue of the science of complex systems is the quantitative characterization of complexity. In the present work we address this issue by resorting to information geometry. Actually we propose a constructive way to associate to a -…

Mathematical Physics · Physics 2017-12-19 Roberto Franzosi , Domenico Felice , Stefano Mancini , Marco Pettini

Obtaining meaningful quantitative descriptions of the statistical dependence within multivariate systems is a difficult open problem. Recently, the Partial Information Decomposition (PID) was proposed to decompose mutual information (MI)…

Information Theory · Computer Science 2017-02-21 Robin A. A. Ince

We formulate the Riemannian calculus of the probability set embedded with $L^2$-Wasserstein metric. This is an initial work of transport information geometry. Our investigation starts with the probability simplex (probability manifold)…

Differential Geometry · Mathematics 2022-04-05 Wuchen Li

In recent years, the unified theory of information and thermodynamics has been intensively discussed in the context of stochastic thermodynamics. The unified theory reveals that information theory would be useful to understand…

Statistical Mechanics · Physics 2018-07-23 Sosuke Ito

What determines whether a molecular property prediction model organizes its representations so that geometric and compositional information can be cleanly separated? We introduce Compositional Probe Decomposition (CPD), which linearly…

Machine Learning · Computer Science 2026-03-10 Joshua Steier

Euclidean distance geometry is the study of Euclidean geometry based on the concept of distance. This is useful in several applications where the input data consists of an incomplete set of distances, and the output is a set of points in…

Quantitative Methods · Quantitative Biology 2012-05-03 Leo Liberti , Carlile Lavor , Nelson Maculan , Antonio Mucherino

The space of probability densities is an infinite-dimensional Riemannian manifold, with Riemannian metrics in two flavors: Wasserstein and Fisher--Rao. The former is pivotal in optimal mass transport (OMT), whereas the latter occurs in…

Differential Geometry · Mathematics 2017-11-21 Klas Modin

Information geometry applies concepts in differential geometry to probability and statistics and is especially useful for parameter estimation in exponential families where parameters are known to lie on a Riemannian manifold. Connections…

Machine Learning · Statistics 2014-05-01 Garvesh Raskutti , Sayan Mukherjee

We construct an information-geometric structure for chemical thermodynamics, applicable to a wide range of chemical reaction systems including non-ideal and open systems. For this purpose, we explicitly construct dual affine coordinate…

Statistical Mechanics · Physics 2022-10-26 Naruo Ohga , Sosuke Ito

Topological data analysis (TDA), while abstract, allows a characterization of time-series data obtained from nonlinear and complex dynamical systems. Though it is surprising that such an abstract measure of structure - counting pieces and…

Computational Geometry · Computer Science 2020-01-07 Nicole Sanderson , Elliott Shugerman , Samantha Molnar , James D. Meiss , Elizabeth Bradley

We call for a theory of the particle-scale structure of materials that is based on the general notion of information rather than its special case of symmetry. An inherent limitation to the symmetry-based understanding of structure is…

Materials Science · Physics 2024-08-13 Glenn D. Hibbard , John Çamkıran

Information theory is an outstanding framework to measure uncertainty, dependence and relevance in data and systems. It has several desirable properties for real world applications: it naturally deals with multivariate data, it can handle…

Machine Learning · Statistics 2024-10-30 Valero Laparra , J. Emmanuel Johnson , Gustau Camps-Valls , Raul Santos-Rodríguez , Jesus Malo

A primary hypothesis that drives scientific and engineering studies is that data has structure. The dominant paradigms for describing such structure are statistics (e.g., moments, correlation functions) and signal processing (e.g.,…

Algebraic Topology · Mathematics 2020-11-11 Alexander D. Smith , Pawel Dlotko , Victor M. Zavala