A mathematical perspective on transformers
From MaRDI portal
Asymptotic properties of solutions to ordinary differential equations (34D05) Synchronization of solutions to ordinary differential equations (34D06) Vlasov equations (35Q83) Packing and covering in (n) dimensions (aspects of discrete geometry) (52C17) Interacting particle systems in time-dependent statistical mechanics (82C22)
Cites work
- L^p theory for the multidimensional aggregation equation
- A brief survey on the approximation theory for sequence modelling
- A class of dimension-free metrics for the convergence of empirical measures
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A consensus-based global optimization method for high dimensional machine learning problems
- A consensus-based model for global optimization and its mean-field limit
- A discrete nonlinear and non-autonomous model of consensus formation
- A nonlinear model of opinion formation on the sphere
- A Problem in Geometric Probability.
- A proof of the Kuramoto conjecture for a bifurcation structure of the infinite-dimensional Kuramoto model
- A proposal on machine learning via dynamical systems
- Almost global consensus on the n-sphere
- Approximation by superpositions of a sigmoidal function
- Approximation Theory and Harmonic Analysis on Spheres and Balls
- Asymptotic phase-locking dynamics and critical coupling strength for the Kuramoto model
- Clustering and asymptotic behavior in opinion formation
- Collective synchronization of classical and quantum oscillators
- Contractivity of transport distances for the kinetic Kuramoto equation
- Control on the manifolds of mappings with a view to the deep learning
- Deep learning
- Deep learning via dynamical systems: an approximation perspective
- Deep neural networks, generic universal interpolation, and controlled ODEs
- Dense networks that do not synchronize and sparse ones that do
- Emergent Behavior in Flocks
- Energy optimization for distributions on the sphere and improvement to the Welch bounds
- Experimental study of energy-minimizing point configurations on spheres
- Fairness in learning-based sequential decision algorithms: a survey
- From Kuramoto to Crawford: Exploring the onset of synchronization in population of coupled oscillators
- From Newton to Boltzmann: hard spheres and short-range potentials
- Geodesic distance Riesz energy on the sphere
- Global-in-time mean-field convergence for singular Riesz-type diffusive flows
- Global-in-time weak measure solutions and finite-time aggregation for nonlocal interaction equations
- Hessian metric via transport information geometry
- Heterophilious dynamics enhances consensus
- Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions
- High-dimensional probability. An introduction with applications in data science
- scientific article; zbMATH DE number 3524004 (Why is no real title available?)
- scientific article; zbMATH DE number 3615571 (Why is no real title available?)
- scientific article; zbMATH DE number 3629502 (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 3371284 (Why is no real title available?)
- scientific article; zbMATH DE number 3037624 (Why is no real title available?)
- Infinite time aggregation for the critical Patlak‐Keller‐Segel model in ℝ2
- Interpolation, approximation, and controllability of deep neural networks
- Landau damping in the Kuramoto model
- Landau Damping to Partially Locked States in the Kuramoto Model
- Long-time dynamics for a simple aggregation equation on the sphere
- Macroscopic and large scale phenomena: coarse graining, mean field limits and ergodicity. Based on the presentations at the summer school, Enschede, the Netherlands, 2012
- Maximum principle based algorithms for deep learning
- Mean field limit for Coulomb-type flows
- Neural ODE Control for Classification, Approximation, and Transport
- On the complete phase synchronization for the Kuramoto model in the mean-field limit
- On the empirical estimation of integral probability metrics
- On the landscape of synchronization networks: a perspective from nonconvex optimization
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- On the relaxation dynamics of Lohe oscillators on some Riemannian manifolds
- On the trend to global equilibrium for Kuramoto oscillators
- Optimal Transport
- Propagation of chaos: a review of models, methods and applications. II: Applications
- Ramanujan graphs: an introduction
- Sharp uniform-in-time propagation of chaos
- Slow motion of gradient flows
- Sparsity in long-time control of neural ODEs
- Stable architectures for deep neural networks
- Statistical optimal transport. École d'Été de Probabilités de Saint-Flour XLIX -- 2019
- Swarming: hydrodynamic alignment with pressure
- THE GEOMETRY OF DISSIPATIVE EVOLUTION EQUATIONS: THE POROUS MEDIUM EQUATION
- The Speed of Mean Glivenko-Cantelli Convergence
- The Variational Formulation of the Fokker--Planck Equation
- There is no non-zero stable fixed point for dense networks in the homogeneous Kuramoto model
- Turnpike in Lipschitz-nonlinear optimal control
- Turnpike in optimal control of PDEs, ResNets, and beyond
- Uniform in time propagation of chaos for the 2D vortex model and other singular stochastic systems
- Universal approximation bounds for superpositions of a sigmoidal function
- Universal Approximation Power of Deep Residual Neural Networks Through the Lens of Control
- Universal optimality of the E₈ and Leech lattices and interpolation formulas
- Universally optimal distribution of points on spheres
- Upper bounds on coarsening rates
Cited in
(12)- Solutions of stationary McKean-Vlasov equation on a high-dimensional sphere and other Riemannian manifolds
- Expander graphs are globally synchronizing
- Clustering in pure-attention hardmax transformers and its role in sentiment analysis
- Generic controllability of equivariant systems and applications to particle systems and neural networks
- Global energy minimizers for a diffusion-aggregation model on sphere
- Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit
- Synchronization on circles and spheres with nonlinear interactions
- Flows on measure spaces and applications in machine learning. Abstracts from the workshop held March 22--27, 2026
- Formation of clusters and coarsening in weakly interacting diffusions
- A mathematical explanation of transformers
- A Lloyd-stabilized Voronoi particle method
- An Analytical Framework for a Multi-Particle Oja Flow
This page was built for publication: A mathematical perspective on transformers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6964504)
