REVIEW 7 cited by
Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Memory complexity and data scarcity have so far prohibited learning solution operators of partial differential equations (PDEs) at high resolutions. We address these limitations by introducing a new data efficient and highly parallelizable operator learning approach with reduced memory requirement and better generalization, called multi-grid tensorized neural operator (MG-TFNO). MG-TFNO scales to large resolutions by leveraging local and global structures of full-scale, real-world phenomena, through a decomposition of both the input domain and the operator's parameter space. Our contributions are threefold: i) we enable parallelization over input samples with a novel multi-grid-based domain decomposition, ii) we represent the parameters of the model in a high-order latent subspace of the Fourier domain, through a global tensor factorization, resulting in an extreme reduction in the number of parameters and improved generalization, and iii) we propose architectural improvements to the backbone FNO. Our approach can be used in any operator learning setting. We demonstrate superior performance on the turbulent Navier-Stokes equations where we achieve less than half the error with over 150x compression. The tensorization combined with the domain decomposition, yields over 150x reduction in the number of parameters and 7x reduction in the domain size without losses in accuracy, while slightly enabling parallelism.
Forward citations
Cited by 7 Pith papers
-
Fourier Neural Operators for Time-Periodic Quantum Systems: Learning Floquet Hamiltonians, Observable Dynamics, and Operator Growth
FNOs learn three maps for time-periodic spin chains (Floquet Hamiltonian, local observables, operator growth) with high accuracy, zero-shot transfer across time grids and driving frequencies, and extrapolation beyond ...
-
Modeling turbulent and self-gravitating fluids with Fourier neural operators
Fourier neural operators trained on 2D projected views of 3D astrophysical simulations can forecast subsequent projected density and velocity snapshots with 5-25% RMS error, though a constant hidden magnetic field mea...
-
LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids
A two-stage Transformer surrogate trained on finite element data predicts stretch-bending final shapes with about 0.17 mm mean absolute distance and over 10,000 times speedup versus FEM.
-
Feature Interaction Modeling for Physics-Informed Neural Networks and Neural Operators
Adding NFM-style bi-interaction layers to PINNs and DeepONets improves accuracy on several high-dimensional smooth PDEs and shock-dominated conservation laws, but not on low-dimensional smooth problems.
-
DRIFT: Direct Reduced Fourier Transforms for Distributed Spectral Neural Operators
Distributed Fourier Neural Operators can compute their truncated spectra with local partial DFTs and two collectives on the kept modes, giving exact results with communication independent of grid resolution.
-
Spectral Embedding via Chebyshev Bases for Robust DeepONet Approximation
Replacing the coordinate-input trunk of a DeepONet with a fixed Chebyshev polynomial dictionary lowers reported reconstruction error on bounded non-periodic PDE benchmarks.
-
Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning
A practical recipe to convert common neural architectures into discretization-agnostic neural operators, validated by Navier-Stokes experiments showing cross-resolution generalization of FNO-style models.
Discussion (0). Sign in to comment.