Metraipolis › archive › dc_cdee9a65cbe3

Neural Symbollic Regression Using Deep Learning and Sparse Modelling — arXiv:2609.01102

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01102
License (as archived)
CC0-1.0
Archived
2026-10-16T15:31:41.368Z
SHA-256 of the archived text
e7f5a85297c075552d2c0d1828a17fc39482cb283c563ab84cb2423c8d4273d1
Stable URL of this page
https://metraipolis.com/documento/dc_cdee9a65cbe3

How to cite

Neural Symbollic Regression Using Deep Learning and Sparse Modelling — arXiv:2609.01102 — arXiv (en), https://arxiv.org/abs/2609.01102 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdee9a65cbe3 (Metraipolis archive dc_cdee9a65cbe3, sha256 e7f5a85297c075552d2c0d1828a17fc39482cb283c563ab84cb2423c8d4273d1)
BibTeX
@misc{dccdee9a65cbe3,
  title = {Neural Symbollic Regression Using Deep Learning and Sparse Modelling — arXiv:2609.01102},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01102},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdee9a65cbe3; sha256 e7f5a85297c075552d2c0d1828a17fc39482cb283c563ab84cb2423c8d4273d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01102. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretability and scientific understanding that exceeds that of black-box models. Nevertheless, traditional methods like Genetic Programming face challenges with scalability and are highly sensitive to noise, while sparse regression techniques such as SINDy rely significantly on predetermined feature libraries. In this work, we present a Neural Symbolic Regression (NSR) framework that treats neural networks as functional preconditioners for symbolic discovery. Our approach uses a decoupled pipeline: a neural network first learns a smooth, noise-robust approximation of the target function in an interaction- aware nonlinear feature space. LASSO is then applied to extract sparse, interpretable closed-form expressions. To improve predictive accuracy and symbolic fidelity by integrating distributed hyperparameter optimization with Ray Tune and ASHA scheduling. Experiments on the Nguyen benchmark suite show that our approach consistently outperforms SINDy and non-tuned neural baselines in RMSE, noise robustness, and out-of-distribution generalization. Ablation studies confirm the significance of feature interactions, neural depth, and tuning strategies. In general, this study presents a scalable and understandable neural-symbolic framework, creating a solid link between neural approximation and the discovery of sparse equations for scientific machine learning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.NE).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Symbolic Computation (cs.SC).
Pagina del lavoro: https://arxiv.org/abs/2609.01102 — 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 2026-10-16T15:12:50.199Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).