# Learning Stiff Dynamical Operators: Scaling, Fast-Slow Excitation, and Eigen-Consistent Neural Models

Source: [Learning Stiff Dynamical Operators: Scaling, Fast-Slow Excitation, and Eigen-Consistent Neural Models](<https://www.sota2.com/research/paper/695c96ea53fdd5c361743503>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-02T05:00:13.059Z

Authors: Mauro Valorani

Published: 2026-01-04T18:30:08.000Z

## Abstract

Stiff dynamical systems represent a central challenge in multi scale modeling across combustion, chemical kinetics, and nonlinear dynamical systems. Neural operator learning has recently emerged as a promising approach to approximate dynamical generators from data, yet stiffness imposes severe obstacles: training errors concentrate on slow manifold states, collapse of fast dynamics occurs, and the learned operator may fail to reproduce the true eigenstructure.   We demonstrate three key advances enabling accurate learning of stiff operators and preserving spectral fidelity: (i) stiffness aware scaling of time derivatives, (ii) fast direction excitation via local trajectory cloud bursts, and (iii) autograd-based Jacobian diagnostics ensuring eigenstructure fidelity. Applied to the Davis-Skodje system, the approach recovers both slow and fast modes across stiffness regimes, reducing fast eigenvalue error by an order of magnitude while improving rollout fidelity. These results argue that spectral fidelity - not trajectory accuracy alone - should be a first-class target in data driven learning of stiff operators.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.01632>)

[PDF](<https://arxiv.org/pdf/2601.01632.pdf>)
