Measure-to-measure interpolation using transformers
From MaRDI portal
Cites work
- A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
- A mathematical perspective on transformers
- A nonholonomic Moser theorem and optimal transport
- Approximate and exact controllability of the continuity equation with a localized vector field
- Clustering in pure-attention hardmax transformers and its role in sentiment analysis
- Constructive approximate transport maps with normalizing flows
- Control and nonlinearity.
- Control in the spaces of ensembles of points
- Control on the manifolds of mappings with a view to the deep learning
- Controllability on the group of diffeomorphisms
- Deep learning approximation of diffeomorphisms via linear-control systems
- Deep learning via dynamical systems: an approximation perspective
- Generic controllability of equivariant systems and applications to particle systems and neural networks
- Interpolation, approximation, and controllability of deep neural networks
- Neural ODE Control for Classification, Approximation, and Transport
- Optimal Transport Over a Linear Dynamical System
- Optimal transportation under nonholonomic constraints
- Polar factorization and monotone rearrangement of vector‐valued functions
- Polar factorization of maps on Riemannian manifolds
- Quantitative stability of optimal transport maps under variations of the target measure
- Universal Approximation Power of Deep Residual Neural Networks Through the Lens of Control
- Weighted Csiszár-Kullback-Pinsker inequalities and applications to transportation inequalities
This page was built for publication: Measure-to-measure interpolation using transformers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7446924)