Mixed Materials
Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems
| Τίτλος: | Temporal Lifting as Latent-Space Regularization for Continuous-Time Flow Models in AI Systems |
|---|---|
| Additional Titles: | We present a latent-space formulation of adaptive temporal lifting for continuous-time dynamical systems. The method introduces a smooth monotone mapping $t \mapsto τ(t)$ that regularizes near-singular behavior of the underlying flow while preserving its conservation laws. In the lifted coordinate, trajectories such as those of the incompressible Navier-Stokes equations on the torus $\mathbb{T}^3$ become globally smooth. From the standpoint of machine-learning dynamics, temporal lifting acts as a continuous-time normalization operator that can stabilize physics-informed neural networks and other latent-flow architectures used in AI systems. The framework links analytic regularity theory with representation-learning methods for stiff or turbulent processes. |
| Συγγραφείς: | Camlin, Jeffrey |
| Στοιχεία εκδότη: | 2025-10-10 2026-01-27 |
| Τύπος εγγράφου: | Mixed materials |
| Περίληψη: | 7 pages, 1 figure, 1 table, 1 algorithm |
| Όροι ευρετηρίου: | Machine Learning, Artificial Intelligence, 35Q30, 76D05, 65M70, 68T07, 68T27, 03D45, I.2.0, text |
| Σύνδεσμος: | |
| Διαθεσιμότητα: | Open access content. Open access content |
| Other Numbers: | COO oai:arXiv.org:2510.09805 1577685968 |
| Πηγή συνεισφοράς: | CORNELL UNIV From OAIster®, provided by the OCLC Cooperative. |
| Αριθμός Καταχώρησης: | edsoai.on1577685968 |
| Βάση Δεδομένων: | OAIster |
| Η περιγραφή δεν είναι διαθέσιμη |