Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model
cond-mat.stat-mech, cs.LG
Submitted: 2026-01-27
Updated: 2026-09-13
Comments: This version matches the published one in Chaos Journal. Preliminary results were presented in November 2025 at the IUPAP Conference on Computational Physics, CP2025 XXXVI, Oak Ridge National Laboratory in Oak Ridge
Journal ref: Chaos 36, 093126 (2026)
DOI: 10.1063/5.0335458
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Low-dimensional embeddings of high-dimensional data
- Learning Geometry and Topology via Multi-Chart Flows
- TensorFlow: A system for large-scale machine learning
- SOAP: Improving and Stabilizing Shampoo using Adam
- Manifold Dimension Estimation via Local Graph Structure
- An Intrinsic Approach to Scalar-Curvature Estimation for Point Clouds
Related papers
- Decoherence-controlled collective criticality in a two-dimensional quantum Stag Hunt
- Measurement-induced phase transitions in disordered fermions
- Quantum Thermalization beyond Non-Integrability and Quantum Scars in a Multispecies Bose-Josephson Junction
- Quantum many-body operator cascade as a route to chaos
- Proof of the absence of local conserved quantities in the Holstein model
- Work fluctuation speed limit in boundary conformal field theories