`tltorch`.TTTensor¶

class tltorch.TTTensor(*args, **kwargs)[source]¶

Tensor-Train (Matrix-Product-State) Factorization

Parameters:

Attributes:

decomposition: Returns the factors and parameters composing the tensor in factorized form

Methods

`from_tensor`(tensor[, rank])	Create a factorized tensor by decomposing a dense tensor
`new`(shape, rank[, device, dtype])	Main way to create a factorized tensor
`normal_`([mean, std])	Inialize the factors of the factorization such that the reconstruction follows a Gaussian distribution
`to_tensor`()	Reconstruct the full tensor from its factorized form
`transduct`(new_dim[, mode, new_factor])	Transduction adds a new dimension to the existing factorization

init_from_tensor

classmethod new(shape, rank, device=None, dtype=None, **kwargs)[source]¶

Main way to create a factorized tensor

Parameters:

shapetuple[int]: shape of the factorized tensor to create
rankint, ‘same’ or float, default is ‘same’: rank of the decomposition
factorization{‘CP’, ‘TT’, ‘Tucker’}, optional: Tensor factorization to use to decompose the tensor, by default ‘Tucker’

Returns:

Raises:

Examples

Create a Tucker tensor of shape (3, 4, 2) with half the parameters as a dense tensor would:

>>> tucker_tensor = FactorizedTensor.new((3, 4, 2)), rank=0.5, factorization='tucker')

classmethod from_tensor(tensor, rank='same', **kwargs)[source]¶

Create a factorized tensor by decomposing a dense tensor

Parameters:

tensortorch.tensor: tensor to factorize
rankint, ‘same’ or float: rank of the decomposition
factorization{‘CP’, ‘TT’, ‘Tucker’}, optional: Tensor factorization to use to decompose the tensor, by default ‘CP’

Returns:

Raises:

property decomposition¶: Returns the factors and parameters composing the tensor in factorized form

normal_(mean=0, std=1)[source]¶

Inialize the factors of the factorization such that the reconstruction follows a Gaussian distribution

Parameters:

Returns:

transduct(new_dim, mode=0, new_factor=None)[source]¶

Transduction adds a new dimension to the existing factorization

Parameters:

new_dimint: dimension of the new mode to add
modewhere to insert the new dimension, after the channels, default is 0: by default, insert the new dimensions before the existing ones (e.g. add time before height and width)

Returns:

tltorch.TTTensor¶