Data-driven Koopman mode approximation: A neural power iteration algorithm
eess.SY, cs.LG, cs.SY, math.OC
Submitted: 2026-08-27
Updated: 2026-09-20
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- An Introductory Guide to Koopman Learning
- World Models
- A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures
- Decoupled Weight Decay Regularization
- Neural Tangent Kernel: A Survey
Related papers
- One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
- A Geometric Decision Procedure for STL Feasibility and Repair
- Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
- Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
- Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
- Decentralized Power-Optimal Coordination for Spacecraft Swarms Using Time-Varying Magnetorquer Actuation