The Adaptive Vekua Cascade: A Differentiable Spectral-Analytic Solver for Physics-Informed Representation
This work addresses memory-efficient and spectrally accurate scientific machine learning for physics simulations, establishing a new paradigm rather than being incremental.
The paper tackles the problems of spectral bias and the curse of dimensionality in coordinate-based neural networks for representing physical fields, proposing the Adaptive Vekua Cascade (AVC) which achieves state-of-the-art accuracy with orders of magnitude fewer parameters (e.g., 840 vs. 4.2 million) and 2-3x faster convergence.
Coordinate-based neural networks have emerged as a powerful tool for representing continuous physical fields, yet they face two fundamental pathologies: spectral bias, which hinders the learning of high-frequency dynamics, and the curse of dimensionality, which causes parameter explosion in discrete feature grids. We propose the Adaptive Vekua Cascade (AVC), a hybrid architecture that bridges deep learning and classical approximation theory. AVC decouples manifold learning from function approximation by using a deep network to learn a diffeomorphic warping of the physical domain, projecting complex spatiotemporal dynamics onto a latent manifold where the solution is represented by a basis of generalized analytic functions. Crucially, we replace the standard gradient-descent output layer with a differentiable linear solver, allowing the network to optimally resolve spectral coefficients in a closed form during the forward pass. We evaluate AVC on a suite of five rigorous physics benchmarks, including high-frequency Helmholtz wave propagation, sparse medical reconstruction, and unsteady 3D Navier-Stokes turbulence. Our results demonstrate that AVC achieves state-of-the-art accuracy while reducing parameter counts by orders of magnitude (e.g., 840 parameters vs. 4.2 million for 3D grids) and converging 2-3x faster than implicit neural representations. This work establishes a new paradigm for memory-efficient, spectrally accurate scientific machine learning. The code is available at https://github.com/VladimerKhasia/vecua.