Metraipolis › archive › dc_bd82ea1ac352

MorphingNet: Symbolic Regression Where the Network Is the Formula — arXiv:2610.19942

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19942
License (as archived): CC0-1.0
Archived: 2026-10-15T14:19:01.441Z
SHA-256 of the archived text: 4dc093e8e0cbd808f9f11d69a5762fc88ef1a65505d09cc04da278ff8a54cb00
Stable URL of this page: https://metraipolis.com/documento/dc_bd82ea1ac352

How to cite

MorphingNet: Symbolic Regression Where the Network Is the Formula — arXiv:2610.19942 — arXiv (en), https://arxiv.org/abs/2610.19942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd82ea1ac352 (Metraipolis archive dc_bd82ea1ac352, sha256 4dc093e8e0cbd808f9f11d69a5762fc88ef1a65505d09cc04da278ff8a54cb00)

BibTeX

@misc{dcbd82ea1ac352,
  title = {MorphingNet: Symbolic Regression Where the Network Is the Formula — arXiv:2610.19942},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19942},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd82ea1ac352; sha256 4dc093e8e0cbd808f9f11d69a5762fc88ef1a65505d09cc04da278ff8a54cb00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce MorphingNet, a network for symbolic regression (SR) whose units change their function continuously. Instead of searching over expressions built from a fixed operator library, MorphingNet trains the form of each function as a parameter, so SR becomes one continuous optimization problem. Its units are either pole-free rational functions or complex exponential--logarithm functions, which move between exponentials, sinusoids, damped oscillations, power laws and logarithms as their parameters change. The network is a readable formula at every step of training, and no operator library is needed to train it; a structure-recovery step afterwards rewrites the trained formula into short elementary expressions. Training is dense linear algebra, so it is GPU-friendly and scales to large data. MorphingNet achieves state-of-the-art accuracy on SRBench, recovers most generating formulas on synthetic benchmarks, and on large data is up to two orders of magnitude faster than the strongest search method. By turning the search for a formula into the training of a network, MorphingNet offers a new paradigm for SR and for scientific discovery from data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19942 — 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 2026-10-15T13:53:35.678Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).