English
Related papers

Related papers: General Riemannian SOM

200 papers

We describe for any Riemannian manifold a certain infinitesimal neighbourhood of the diagonal. Semi-conformal maps are analyzed as those that preserve such neighbourhoods; harmonic maps are analyzed as those that preserve mirror image…

Differential Geometry · Mathematics 2007-05-23 Anders Kock

Recent studies on deep neural networks show that flat minima of the loss landscape correlate with improved generalization. Sharpness-aware minimization (SAM) efficiently finds flat regions by updating the parameters according to the…

Machine Learning · Computer Science 2025-02-13 Albert Kjøller Jacobsen , Georgios Arvanitidis

Continuous monitoring with an ever-increasing number of sensors has become ubiquitous across many application domains. However, acquired time series are typically high-dimensional and difficult to interpret. Expressive deep learning (DL)…

Machine Learning · Computer Science 2023-05-26 Iris A. M. Huijben , Arthur A. Nijdam , Sebastiaan Overeem , Merel M. van Gilst , Ruud J. G. van Sloun

We extend the recently developed discrete geometric singular perturbation theory to the non-normally hyperbolic regime. Our primary tool is the Takens embedding theorem, which provides a means of approximating the dynamics of particular…

Dynamical Systems · Mathematics 2024-08-13 Samuel Jelbart , Christian Kuehn

We prove that harmonic maps into Euclidean buildings, which are not necessarily locally finite, have singular sets of Hausdorff codimension 2, extending the locally finite regularity result of Gromov and Schoen. As an application, we prove…

Differential Geometry · Mathematics 2026-05-04 Christine Breiner , Ben K. Dees , Chikako Mese

In numerous applicative contexts, data are too rich and too complex to be represented by numerical vectors. A general approach to extend machine learning and data mining techniques to such data is to really on a dissimilarity or on a kernel…

Machine Learning · Statistics 2014-07-03 Fabrice Rossi

Embedding graphs in continous spaces is a key factor in designing and developing algorithms for automatic information extraction to be applied in diverse tasks (e.g., learning, inferring, predicting). The reliability of graph embeddings…

Machine Learning · Computer Science 2023-11-30 Andrea Marinoni , Pietro Lio' , Alessandro Barp , Christian Jutten , Mark Girolami

A work of Manton showed how skymions may be viewed as maps between riemannian manifolds minimising an energy functional, with topologically non-trivial global minimisers given precisely by isometries. We consider a generalisation of this…

Differential Geometry · Mathematics 2023-10-03 Josh Cork , Derek Harland

In the present article the geometry of semi-Riemannian manifolds with nonholonomic constraints is studied. These manifolds can be considered as analogues to the sub-Riemannian manifolds, where the positively definite metric is substituted…

Differential Geometry · Mathematics 2009-01-13 Anna Korolko , Irina Markina

Geodesic regression has been proposed for fitting the geodesic curve. However, it cannot automatically choose the dimensionality of data. In this paper, we develop a Bayesian geodesic regression model on Riemannian manifolds (BGRM) model.…

Computer Vision and Pattern Recognition · Computer Science 2020-09-16 Youshan Zhang

Many domains, from deep learning to finance, require compounding real numbers over long sequences, often leading to catastrophic numerical underflow or overflow. We introduce generalized orders of magnitude (GOOMs), a principled extension…

Machine Learning · Computer Science 2025-10-10 Franz A. Heinsen , Leo Kozachkov

The problem of determining the configuration of points from partial distance information, known as the Euclidean Distance Geometry (EDG) problem, is fundamental to many tasks in the applied sciences. In this paper, we propose two algorithms…

Optimization and Control · Mathematics 2024-10-10 Chandler Smith , HanQin Cai , Abiy Tasissa

We propose a unified view on two widely used data visualization techniques: Self-Organizing Maps (SOMs) and Stochastic Neighbor Embedding (SNE). We show that they can both be derived from a common mathematical framework. Leveraging this…

Machine Learning · Computer Science 2022-05-04 Thibaut Kulak , Anthony Fillion , François Blayo

We study the size of the isometry group Isom(M, g) of Riemannian manifolds (M, g) as g varies. For M not admitting a circle action, we show that the order of Isom(M, g) can be universally bounded in terms of the bounds on Ricci curvature,…

Differential Geometry · Mathematics 2014-05-12 Wouter van Limbeek

We study optimization over Riemannian embedded submanifolds, where the objective function is relatively smooth in the ambient Euclidean space. Such problems have broad applications but are still largely unexplored. We introduce two…

Optimization and Control · Mathematics 2025-08-08 Chang He , Jiaxiang Li , Bo Jiang , Shiqian Ma , Shuzhong Zhang

Morse functions with exactly two singular points on spheres and canonical projections of spheres belong to the class of a certain good class of smooth maps: special generic maps. We mainly investigate information on cohomology of closed and…

Algebraic Topology · Mathematics 2022-09-13 Naoki Kitazawa

Color names based image representation is successfully used in person re-identification, due to the advantages of being compact, intuitively understandable as well as being robust to photometric variance. However, there exists the diversity…

Computer Vision and Pattern Recognition · Computer Science 2017-07-11 Yang Yang , Shengcai Liao , Zhen Lei , Stan Z. Li

A smooth map between smooth manifolds is called a special generic map if it has only definite fold points as its singularities. In this paper, we give conditions for a special generic map into the 3-dimensional Euclidean space to be…

Geometric Topology · Mathematics 2016-03-16 Masayuki Nishioka

Exchangeable graph models (ExGM) subsume a number of popular network models. The mathematical object that characterizes an ExGM is termed a graphon. Finding scalable estimators of graphons, provably consistent, remains an open issue. In…

Methodology · Statistics 2014-02-12 Stanley H. Chan , Edoardo M. Airoldi

In Artificial Intelligence (AI) and computational science, learning the mappings between functions (called operators) defined on complex computational domains is a common theoretical challenge. Recently, Neural Operator emerged as a…

Numerical Analysis · Mathematics 2023-12-13 Gengxiang Chen , Xu Liu , Qinglu Meng , Lu Chen , Changqing Liu , Yingguang Li
‹ Prev 1 4 5 6 7 8 10 Next ›