Learning symmetries and non-Euclidean data representations via collective dynamics of generalized Kuramoto oscillators

DOI10.1016/J.PHYSD.2025.134953MaRDI QIDQ6881484zbMATH OpenFDO

Authors Vladimir Jacimovic, Ron Hommelsheim

Publication date 17 December 2025

Published in Physica D (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.PHYSD.2025.134953

zbMATH Keywords

directional statisticsgeometric deep learningMöbius transformationneural networkstrainable swarms

Mathematics Subject Classification ID

Oscillation theory, zeros, disconjugacy and comparison theory for ordinary differential equations (34C10) Directional data; spatial statistics (62H11) Artificial neural networks and deep learning (68T07)

Cites work

• A distribution for a pair of unit vectors generated by Brownian motion
• A family of distributions on the circle with links to, and applications arising from, Möbius transformation
• A multivariate von mises distribution with applications to bioinformatics
• A Möbius transformation-induced distribution on the torus
• A nonlinear model of opinion formation on the sphere
• A proposal on machine learning via dynamical systems
• An Introduction to Optimization on Smooth Manifolds
• An invariant form for the prior probability in estimation problems
• Collective motions of globally coupled oscillators and some probability distributions on circle
• Conditional inference and Cauchy models
• Conformally natural extension of homeomorphisms of the circle
• Consensus optimization on manifolds
• Constants of motion for superconducting Josephson arrays
• Control theory on Lie groups
• Data-driven science and engineering. Machine learning, dynamical systems, and control
• Deep learning
• Dynamic fuzzy machine learning
• Dynamics in a kinetic model of oriented particles with phase transition
• Emergent dynamics of a generalized Lohe model on some class of Lie groups
• Estimation of non-normalized statistical models by score matching
• Extended information filter on matrix Lie groups
• Fisher information distance: a geometrical reading
• Harmonic and subharmonic function theory on the hyperbolic ball
• High-dimensional Kuramoto models on Stiefel manifolds synchronize complex networks almost globally
• scientific article; zbMATH DE number 1620890 (Why is no real title available?)
• scientific article; zbMATH DE number 5430929 (Why is no real title available?)
• scientific article; zbMATH DE number 1375577 (Why is no real title available?)
• scientific article; zbMATH DE number 3524004 (Why is no real title available?)
• scientific article; zbMATH DE number 3555239 (Why is no real title available?)
• scientific article; zbMATH DE number 3602484 (Why is no real title available?)
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• scientific article; zbMATH DE number 7626752 (Why is no real title available?)
• scientific article; zbMATH DE number 7306852 (Why is no real title available?)
• scientific article; zbMATH DE number 5223994 (Why is no real title available?)
• Hyperbolic geometry of Kuramoto oscillator networks
• Identical phase oscillators with global sinusoidal coupling evolve by Möbius group action
• Improved numerical scheme for the generalized Kuramoto model
• Information geometry
• Information Geometry of the Gaussian Distribution in View of Stochastic Optimization
• Information-geometric optimization algorithms: a unifying picture via invariance principles
• Maximum principle based algorithms for deep learning
• Neural ODEs as the deep limit of ResNets with constant weights
• Non-Abelian Kuramoto models and synchronization
• Normalizing flows for probabilistic modeling and inference
• On synchronization in Kuramoto models on spheres
• Phase coupling estimation from multivariate phase statistics
• Poisson Kernel-Based Clustering on the Sphere: Convergence Properties, Identifiability, and a Method of Sampling
• Recent advances in directional statistics
• Riemannian geometry of Grassmann manifolds with a view on algorithmic computation
• Solvable model of the collective motion of heterogeneous particles interacting on a sphere
• Some properties of a Cauchy family on the sphere derived from the Möbius transformations
• Swarms on the 3-sphere with adaptive synapses: Hebbian and anti-Hebbian learning rule
• Synchronization of Kuramoto oscillators with adaptive couplings
• Systems of matrix Riccati equations, linear fractional transformations, partial integrability and synchronization
• The general non-abelian Kuramoto model on the 3-sphere
• The Kuramoto model on a sphere: explaining its low-dimensional dynamics with group theory and hyperbolic geometry
• The Variational Formulation of the Fokker--Planck Equation
• Weakly connected neural networks

Cited in

(1)

• An Analytical Framework for a Multi-Particle Oja Flow

This page was built for publication: Learning symmetries and non-Euclidean data representations via collective dynamics of generalized Kuramoto oscillators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6881484)