← Back to all news
arXiv Machine Learning By Simon Alford, Edward Gu, Omar Costilla-Reyes, Dan Tamayo, Miles Cranmer, Kevin Ellis

Distilling neural networks into equations to predict planetary instability

Read the original on arXiv Machine Learning →

The paper presents a two‑stage method that first trains a neural network on N‑body simulations of multi‑planet systems and then distills its knowledge into closed‑form algebraic equations via symbolic regression. These distilled equations predict the onset of dynamical instability across a wide range of mass ratios, spacings, and eccentricities, outperforming existing analytic estimates. The approach yields a small set of interpretable variables that capture the structure of the instability landscape.

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 2

Accelerating Chemical Kinetics for Exoplanet Atmospheres using Neural Networks

The paper introduces a neural‑network based local‑box chemical kinetics solver for exoplanet atmospheres, employing a residual flow‑map architecture. It achieves microsecond‑scale inference with percent‑level accuracy across a wide range of temperatures, pressures, time steps, and compositional variations, outperforming other machine‑learning models and handling the extreme stiffness of atmospheric chemistry. The surrogate model offers a flexible, efficient alternative to classical solvers for state‑to‑state flow‑map problems in numerical simulations.

By Isaac Malsky, Xi Zhang, Tiffany Kataria, Matthew Graham, Ziyu Huang, Boris Bonev, Shang-Min Tsai, Elspeth K. H. Lee
More like this →
arXiv Machine Learning
Sep 2

Neural Symbollic Regression Using Deep Learning and Sparse Modelling

Neural Symbolic Regression (NSR) uses neural networks as functional preconditioners to learn smooth, noise‑robust approximations of target functions in an interaction‑aware nonlinear feature space. A subsequent LASSO step extracts sparse, interpretable closed‑form expressions, while distributed hyperparameter optimization with Ray Tune and ASHA scheduling improves predictive accuracy and symbolic fidelity. Experiments on the Nguyen benchmark demonstrate that NSR outperforms SINDy and untuned neural baselines in RMSE, noise robustness, and out‑of‑distribution generalization, with ablation studies highlighting the importance of feature interactions, neural depth, and tuning strategies.

By Ravi Kumar U, Sumitra S
benchmarkssafety
More like this →