apply_model#
- t3toolbox.fitting.apply_model(geometry, x, ww, residual, regularizer=None)#
def apply_model( geometry, # MANIFOLD / COREWISE (or the UNIFORM_* twin for a uniform x) x: typ.Union[t3.TuckerTensorTrain, ut3.UniformTuckerTensorTrain], # the current point ww: typ.Sequence[NDArray], # sample vectors, len=d, elm_shape=W+(Ni,) residual: NDArray, # r = apply(x) − y, shape W+C regularizer: typ.Any = None, # optional regularizer, e.g. optimizers.IdentityRegularizer(λ) ) -> typ.Union[GaussNewtonModel, UniformGaussNewtonModel]:
The Gauss-Newton model of an all-modes
applyleast-squares objective atx, ongeometry.Accepts a ragged
TuckerTensorTrain(->GaussNewtonModel) or a uniformUniformTuckerTensorTrain(->UniformGaussNewtonModel); the representation is inferred fromxand the geometry must match.regularizeraddsρ(x)to the model (ragged only).- Parameters:
x (t3toolbox.backend.common.typ.Union[TuckerTensorTrain, UniformTuckerTensorTrain])
ww (t3toolbox.backend.common.typ.Sequence[NDArray])
residual (NDArray)
regularizer (t3toolbox.backend.common.typ.Any)
- Return type:
t3toolbox.backend.common.typ.Union[GaussNewtonModel, UniformGaussNewtonModel]