Inverse Neural Operator for ODE Parameter Optimization
Not on the map. Why?
Abstract (arXiv)
We propose the Inverse Neural Operator (INO), a two-stage framework for recovering hidden ODE parameters from sparse, partial observations. In Stage 1, a Conditional Fourier Neural Operator (C-FNO) with cross-attention learns a differentiable surrogate that reconstructs full ODE trajectories from arbitrary sparse inputs, suppressing high-frequency artifacts via spectral regularization. In Stage 2, an Amortized Drifting Model (ADM) learns a kernel-weighted velocity field in parameter space, transporting random parameter initializations toward the ground truth without backpropagating through the surrogate, avoiding the Jacobian instabilities that afflict gradient-based inversion in stiff regimes. Experiments on a real-world stiff atmospheric chemistry benchmark (POLLU, 25 parameters) and a synthetic Gene Regulatory Network (GRN, 40 parameters) show that INO outperforms gradient-based and amortized baselines in parameter recovery accuracy while requiring only 0.23s inference time, a 487x speedup over iterative gradient descent.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 49 references that are in the map. First posted on arXiv 12 Mar 2026.
Builds on
30 of 49 references.
References · 30
- 2017Attention Is All You Needcited by 60,361
- 2022Flow Matching for Generative Modelingcited by 5,702
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
- 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
- 2019Machine Learning for Fluid Mechanicscited by 385
- 2020Universal Differential Equations for Scientific Machine Learningcited by 353
18 more
- 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
- 2022U-NO: U-shaped Neural Operatorscited by 230
- 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
- 2021Improved architectures and training algorithms for deep operator networkscited by 86
- 2021Stiff Neural Ordinary Differential Equationscited by 78
- 2022Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modelingcited by 65
- 2023Neural Inverse Operators for Solving PDE Inverse Problemscited by 65
- 2022Generative Adversarial Neural Operatorscited by 52
- 2021Data-driven discovery of Green's functions with human-understandable deep learningcited by 44
- 2024Continuum Attention for Neural Operatorscited by 40
- 2022Learning to Solve PDE-constrained Inverse Problems with Graph Networkscited by 37
- 2022Semi-supervised Invertible Neural Operators for Bayesian Inverse Problemscited by 25
- 2023PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systemscited by 19
- 2024Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problemscited by 19
- 2025KANO: Kolmogorov-Arnold Neural Operatorcited by 7
- 2024Neural Network Emulator for Atmospheric Chemical ODEcited by 5
- 2023CoNO: Complex Neural Operator for Continuous Dynamical Systemscited by 4
- 2025SPIN-ODE: Stiff Physics-Informed Neural ODE for Chemical Reaction Rate Estimationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.