English
Related papers

Related papers: Johnson-Lindenstrauss Lemma Beyond Euclidean Geome…

200 papers

In physics, two systems that radically differ at short scales can exhibit strikingly similar macroscopic behaviour: they are part of the same long-distance universality class. Here we apply this viewpoint to geometry and initiate a program…

High Energy Physics - Theory · Physics 2023-11-22 Adam R. Brown , Michael H. Freedman , Henry W. Lin , Leonard Susskind

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

We take matrix decompositions that are usually applied to matrices over the real numbers or complex numbers, and extend them to matrices over an algebra called the double numbers. In doing so, we unify some matrix decompositions: For…

Rings and Algebras · Mathematics 2021-12-07 Ran Gutin

The set theory relations \in, \backslash, \Delta, \cap, and \cup have corollaries in subspace relations. Geometric Algebra is introduced as the ideal framework to explore these subspace operations. The relations \in, \backslash, and \Delta…

Rings and Algebras · Mathematics 2007-05-23 T. A. Bouma , L. Dorst , H. G. J. Pijls

Generalized tensor analysis in the sense of Colombeau's construction is employed to introduce a nonlinear distributional pseudo-Riemannian geometry. In particular, after deriving several characterizations of invertibility in the algebra of…

Functional Analysis · Mathematics 2007-05-23 Michael Kunzinger , Roland Steinbauer

We show that the range of applicability of the change of representation formula derived in J. Math. Phys. \textbf{54}, 033513 (2013) [arXiv:1302.6928] is very narrow and extend it to include all physical applications, particularly,…

Mathematical Physics · Physics 2014-03-21 Mustapha Azreg-Aïnou

Metric embedding has become a common technique in the design of algorithms. Its applicability is often dependent on how high the embedding's distortion is. For example, embedding finite metric space into trees may require linear distortion…

Data Structures and Algorithms · Computer Science 2007-05-23 Yair Bartal , Manor Mendel

Motivated by the problem of compressing point sets into as few bits as possible while maintaining information about approximate distances between points, we construct random nonlinear maps $\varphi_\ell$ that compress point sets in the…

Computational Geometry · Computer Science 2024-03-05 Brett Leroux , Luis Rademacher

Within a framework of noncommutative geometry, we develop an analogue of (pseudo) Riemannian geometry on finite and discrete sets. On a finite set, there is a counterpart of the continuum metric tensor with a simple geometric…

General Relativity and Quantum Cosmology · Physics 2009-10-31 A. Dimakis , F. Muller-Hoissen

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

Collider searches face the challenge of defining a representation of high-dimensional data such that physical symmetries are manifest, the discriminating features are retained, and the choice of representation is new-physics agnostic. We…

High Energy Physics - Phenomenology · Physics 2023-12-11 Barry M. Dillon , Gregor Kasieczka , Hans Olischlager , Tilman Plehn , Peter Sorrenson , Lorenz Vogel

In high dimension, low sample size (HDLSS) settings, classifiers based on Euclidean distances like the nearest neighbor classifier and the average distance classifier perform quite poorly if differences between locations of the underlying…

Methodology · Statistics 2022-03-08 Sarbojit Roy , Soham Sarkar , Subhajit Dutta , Anil K. Ghosh

Embedding-based representations in Euclidean space $\mathbb{R}^d$ are a cornerstone of modern machine learning, where a major goal is to use the \emph{smallest dimension} that faithfully captures data relations. In this work, we prove sharp…

Data Structures and Algorithms · Computer Science 2026-05-06 Dionysis Arvanitakis , Vaggos Chatziafratis , Yiyuan Luo

In this work, the relativistic phenomena of Lorentz contraction and time dilation are derived using a modified distance formula appropriate for discrete space. This new distance formula is different than Pythagoras's theorem but converges…

General Relativity and Quantum Cosmology · Physics 2018-10-10 David Crouse , Joseph Skufca

This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of…

Machine Learning · Statistics 2008-09-30 Kevin M. Carter , Raviv Raich , Alfred O. Hero

Riemannian neural networks, which extend deep learning techniques to Riemannian spaces, have gained significant attention in machine learning. To better classify the manifold-valued features, researchers have started extending Euclidean…

Machine Learning · Computer Science 2024-10-03 Ziheng Chen , Yue Song , Rui Wang , Xiaojun Wu , Nicu Sebe

In this work, we study distance metric learning (DML) for high dimensional data. A typical approach for DML with high dimensional data is to perform the dimensionality reduction first before learning the distance metric. The main…

Machine Learning · Computer Science 2015-09-16 Qi Qian , Rong Jin , Lijun Zhang , Shenghuo Zhu

Three different representation of the proper Euclidean geometry are considered. They differ in the number of basic elements, from which the geometrical objects are constructed. In E-representation there are three basic elements (point,…

General Mathematics · Mathematics 2011-03-03 Yuri A. Rylov

Many interesting machine learning problems are best posed by considering instances that are distributions, or sample sets drawn from distributions. Previous work devoted to machine learning tasks with distributional inputs has done so…

Machine Learning · Statistics 2021-01-15 Danica J. Sutherland , Junier B. Oliva , Barnabás Póczos , Jeff Schneider

The deformation principle admits one to obtain a very broad class of nonuniform geometries as a result of deformation of the proper Euclidean geometry. The Riemannian geometry is also obtained by means of a deformation of the Euclidean…

General Mathematics · Mathematics 2007-05-23 Yuri A. Rylov