Preprint
Aug 2026
Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics
An eigenanalysis framework is developed that reveals the dynamical origin of inference-time error growth and introduces a stability-promoting loss that explicitly regularizes Jacobian-driven error amplification, improving both forecast accuracy and dynamical robustness.
C. Ainslie, P. Hassanzadeh, Michael W. Mahoney et al.
· 0 citations