aiqbench analysis
MorphingNet advances symbolic regression by treating function forms as continuous trainable parameters, enabling the network to seamlessly transition between mathematical operations like exponentials and sinusoids during optimization. This approach transforms formula discovery into a dense linear algebra problem, offering significant speedups over traditional search methods while maintaining high accuracy on scientific benchmarks. By eliminating the need for fixed operator libraries, this method provides a novel paradigm for extracting interpretable equations directly from data.
MorphingNet: Symbolic Regression Where the Network Is the Formula
arXiv:2610.19942v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2610.19942 [cs.LG]
(or arXiv:2610.19942v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.19942 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 265 words
Related coverage
Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles
arXiv · Jul 23, 2026
Kolmogorov-Arnold networks in nuclear binding energy prediction
arXiv · Sep 30, 2026
Explainable Machine Learning for Multilayer Planar Winding Inductance Estimation
arXiv · Sep 30, 2026
Searching the Space of Feed-Forward Neural-Network Weight-Update Rules with Fixed Depth Symbolic Regression
arXiv · Jul 27, 2026