← Back to all news
arXiv Machine Learning By Shreeyam Bangera, Manya Gupta

When Does Jacobian Fine-Tuning Stabilize Neural PDE Emulators?

Read the original on arXiv Machine Learning →

The study investigates how Jacobian-based fine‑tuning affects neural emulators of chaotic partial differential equations (PDEs). By decomposing error growth into physical and model‑induced components, the authors introduce an amplification ratio that quantifies how the emulator’s dynamics magnify prediction errors. Across 21 experimental setups, Jacobian fine‑tuning significantly reduced errors—especially for configurations with high amplification ratios—while matching the solver’s Jacobian along the model’s error direction (EDJM) outperformed random directions and input‑noise injection.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 7

Second-order consistency for learning chaotic dynamics via randomized Jacobian matching

The paper introduces a method called model‑constrained randomized Jacobian matching to enforce second‑order consistency when learning chaotic dynamical systems. By comparing Jacobians at randomly perturbed inputs, the approach implicitly penalises Hessian mismatch without computing full Hessian tensors, achieving $O(d^2)$ memory cost. Experiments on Lorenz 63 and Lorenz 96 show that this second‑order supervision reduces invariant‑measure error, improves Lyapunov‑spectrum accuracy, and avoids spurious attractors that plague first‑order methods.

By Shinhoo Kang, Hai V. Nguyen, Tan Bui-Thanh
More like this →
arXiv Machine Learning
Oct 12

Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields

Neural surrogates for forecasting physical fields from sparse, noisy sensors typically use a spatial window and a temporal history of past snapshots. This study compares the trade‑off between window size and history length against the Bayes‑optimal error, showing that for fields with local dynamics the optimal forecast relies mainly on distant sensors via spatial correlation. Experiments on Burgers flow and the chaotic Kuramoto‑Sivashinsky equation reveal that the benefit of additional snapshots depends on lead time and system stability, leading to design rules that size the window in correlation lengths and split input budgets between window and history based on forecast horizon.

By Ruige Kong
More like this →
arXiv Machine Learning
Aug 7

Scientific Machine Learning of Chaotic Systems Learns Reduced-Order Equations for Neural Populations

arXiv:2507. 03631v4 Announce Type: replace Abstract: Extracting interpretable mathematical models from complex dynamical systems is difficult, especially for chaotic dynamics observed with noisy experimental data.

By Anthony G. Chesebro, David Hofmann, Vaibhav Dixit, Earl K. Miller, Richard H. Granger, Alan Edelman, Christopher V. Rackauckas, Lilianne R. Mujica-Parodi, Helmut H. Strey
benchmarkssafety
More like this →