AI & ML Efficiency Breakthrough

Recovers hidden ODE parameters from sparse data with a 487x speedup over gradient-based methods.

arXiv · March 13, 2026 · 2603.11854

Zhi-Song Liu, Wenqing Peng, Helmi Toropainen, Ammar Kheder, Andreas Rupp, Holger Froning, Xiaojie Lin, Michael Boy

Why it matters

The Inverse Neural Operator (INO) bypasses Jacobian instabilities in stiff regimes by using a drifting model in parameter space. This allows for near-instantaneous (0.2s) system identification in complex fields like atmospheric chemistry and gene regulation.

From the abstract

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, trans