# DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement

arXiv: https://arxiv.org/abs/2609.00530 · HTML: https://mlsanity.com/paper/2609.00530/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients](https://mlsanity.com/paper/1912.04871/) (2019)
- [Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl](https://mlsanity.com/paper/2305.01582/) (2023)
- [Symbolic Regression for PDEs using Pruned Differentiable Programs](https://mlsanity.com/paper/2303.07009/) (2023)
- [Genetic Programming Based Symbolic Regression for Analytical Solutions to Differential Equations](https://mlsanity.com/paper/2302.03175/) (2023)
- [StruSR: Structure-Aware Symbolic Regression with Physics-Informed Taylor Guidance](https://mlsanity.com/paper/2510.06635/) (2025)
- [Physics Informed Symbolic Networks](https://mlsanity.com/paper/2207.06240/) (2022)
- [SymTorch: Symbolic Distillation of Neural Networks](https://mlsanity.com/paper/2602.21307/) (2026)
- [A Data-Free Symbolic Regression Approach for Solving Equations](https://mlsanity.com/paper/2606.07152/) (2026)

## Abstract (arXiv)

Recovering compact explicit solutions from neural approximations is challenging when imperfect teacher data guide symbolic topology search and coefficient estimation. We present DeSyR, a decoupled symbolic recovery framework for differential equations. A physics-informed neural network guides repeated searches to construct candidate topologies with provisional constants. Once a topology is fixed, its coefficients are refined solely from the governing equation and prescribed constraints, followed by gated selection and verification. For linear fixed-topology parameterizations, we characterize teacher-error inheritance and show that finite-weight mixed data--physics fitting retains an O(β-1) teacher-dependent contribution when the teacher error projects onto the model space. Under well-posedness, representability, zero-residual attainment, and discrete determinacy, physics-only refinement conditionally recovers exact coefficients; for nonlinear parameterizations, the corresponding guarantees are local. DeSyR is evaluated on 15 differential-equation problems across 18 configurations covering high-order, space--time, multidimensional, nonlinear, and coupled systems. A candidate-level audit yields a 99.23% convergence rate among free-parameter refits, while every selected refinement involving free coefficients converges. Configuration-level median refined relative L2 errors are 2.31×10-14 or lower. In same-topology comparisons, refinement reduces error by eight to fourteen orders of magnitude. These results show that an approximate neural teacher can guide topology discovery without imposing its error scale on final recovered coefficients, provided a target-capable topology is retained and physics-only refinement converges.