Metraipolis › archive › dc_d7a5e5bdff56
A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63 — arXiv:2610.06798
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06798
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:32:35.419Z
- SHA-256 of the archived text
d745d8bb328e19baf4a36d8a2d5fe74411c52ae8291625fdeee0747c3918239d- Stable URL of this page
https://metraipolis.com/documento/dc_d7a5e5bdff56
How to cite
A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63 — arXiv:2610.06798 — arXiv, https://arxiv.org/abs/2610.06798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7a5e5bdff56 (Metraipolis archive dc_d7a5e5bdff56, sha256 d745d8bb328e19baf4a36d8a2d5fe74411c52ae8291625fdeee0747c3918239d)
BibTeX
@misc{dcd7a5e5bdff56,
title = {A Response Theory Probe for Learned Stochastic AI Simulators, Tested on Lorenz-63 — arXiv:2610.06798},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06798},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7a5e5bdff56; sha256 d745d8bb328e19baf4a36d8a2d5fe74411c52ae8291625fdeee0747c3918239d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine-learning emulators of chaotic and stochastic systems are usually validated on forecast skill and long-run statistics. Neither certifies that an emulator responds correctly to forcing, the property that projection and attribution studies rely on. Linear response theory makes this testable: the forced response follows from unperturbed correlations through a generalized fluctuation-dissipation relation, and decomposes over the stochastic Ruelle-Pollicott resonances of the Koopman generator. Building on the Koopmanism Response framework, we turn this into a calibrated, mode-resolved test for learned surrogates: each surrogate rollout passes or fails each check, and failure rates are compared with those of independent realizations of the true system. On stochastic Lorenz-63, a three-variable toy model, we evaluate SINDy, an MLP, a reservoir computer, a neural ODE and a neural SDE with learned diffusion, over up to 80 rollouts each. A sparse-regression model with the correct library passes every check at rates consistent with the true system. Invariant-statistics fidelity and response fidelity dissociate in both directions: a quarter of reservoir-computer rollouts pass every invariant-statistics check and match the static susceptibility $\chi(0)$, yet misrepresent the slow relaxation modes, while the neural ODE and SDE rarely meet the invariant-statistics floor but recover those modes in three quarters of rollouts. As expected of a time-integrated quantity dominated here by fast relaxation, $\chi(0)$ does not separate these cases. For a fixed network, the training formulation (one-step drift, flow map, or multi-step through the integrator) decides which of these properties it gets right. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Dynamical Systems (math.DS) ; Machine Learning (cs.LG); Chaotic Dynamics (nlin.CD). Pagina del lavoro: https://arxiv.org/abs/2610.06798 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:06.052Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).