Operator learning

34 papers with code • 0 benchmarks • 0 datasets

Learn an operator between infinite dimensional Hilbert spaces or Banach spaces

Most implemented papers

Convolutional Analysis Operator Learning: Acceleration and Convergence

mechatoz/convolt 15 Feb 2018

This paper proposes a new convolutional analysis operator learning (CAOL) framework that learns an analysis sparsifying regularizer with the convolution perspective, and develops a new convergent Block Proximal Extrapolated Gradient method using a Majorizer (BPEG-M) to solve the corresponding block multi-nonconvex problems.

Convolutional Analysis Operator Learning: Dependence on Training Data

dahong67/ConvolutionalAnalysisOperatorLearning.jl 21 Feb 2019

Convolutional analysis operator learning (CAOL) enables the unsupervised training of (hierarchical) convolutional sparsifying operators or autoencoders from large datasets.

Physics-Informed Neural Operator for Learning Partial Differential Equations

devzhk/PINO 6 Nov 2021

This is because PINO learns the solution operator by optimizing PDE constraints on multiple instances while PINN optimizes PDE constraints of a single PDE instance.

Importance Weight Estimation and Generalization in Domain Adaptation under Label Shift

kazizzad/LabelShiftEstimator 29 Nov 2020

We deploy these estimators and provide generalization bounds in the unlabeled target domain.

Learning Symbolic Operators for Task and Motion Planning

ronuchit/LOFT_IROS_2021 28 Feb 2021

We then propose a bottom-up relational learning method for operator learning and show how the learned operators can be used for planning in a TAMP system.

Choose a Transformer: Fourier or Galerkin

scaomath/galerkin-transformer NeurIPS 2021

Without softmax, the approximation capacity of a linearized Transformer variant can be proved to be comparable to a Petrov-Galerkin projection layer-wise, and the estimate is independent with respect to the sequence length.

Neural Operator: Learning Maps Between Function Spaces

zongyi-li/fourier_neural_operator 19 Aug 2021

The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets.

Multiwavelet-based Operator Learning for Differential Equations

gaurav71531/mwt-operator NeurIPS 2021

The solution of a partial differential equation can be obtained by computing the inverse operator map between the input and the solution space.

Improved architectures and training algorithms for deep operator networks

predictiveintelligencelab/improveddeeponets 4 Oct 2021

In this work we analyze the training dynamics of deep operator networks (DeepONets) through the lens of Neural Tangent Kernel (NTK) theory, and reveal a bias that favors the approximation of functions with larger magnitudes.

Fast PDE-constrained optimization via self-supervised operator learning

predictiveintelligencelab/pde-constrained-optimization-pi-deeponet 25 Oct 2021

Design and optimal control problems are among the fundamental, ubiquitous tasks we face in science and engineering.