SLiM: Structured Linear Maps¶
This package provides a suite of structured linear maps which can be used as drop-in replacements for PyTorch’s nn.Linear module. Recent work viewing neural networks from a dynamical systems perspective has introduced a host of parametrizations for the basic linear maps which are subcomponents of neural networks. Such parametrizations may enhance the stability of learning, and embed models with inductive priors that encode domain application knowledge. This package is an effort to collect these all in one place with a common API to facilitate rapid exploration.
Note
We encourage folks to contribute any new structured linear maps as feature requests.
Linear Map |
class |
|---|---|
Benchmarks¶
Sequence to Classification:
Point to Classification:
Sequence to Regression:
Point to Regression:
Dynamics:
Building models
Docs:
- Linear
BoundedNormLinearButterflyLinearDampedSkewSymmetricLinearGershgorinLinearHprod()IdentityGradReLUIdentityInitLinearIdentityLinearL0LinearLassoLinearLassoLinearRELULeftStochasticLinearLinearLinearBaseNonNegativeLinearOrthogonalLinearPSDLinearPerronFrobeniusLinearRightStochasticLinearSVDLinearSVDLinearLearnBoundsSchurDecompositionLinearSkewSymmetricLinearSpectralLinearSplitLinearSquareLinearStableSplitLinearSymmetricLinearSymmetricSVDLinearSymmetricSpectralLinearSymplecticLinearTrivialNullSpaceLinear
- RNN
- Benchmarks