Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the user guide for the big picture.

3.3.6. fmralign.alignment_methods.OptimalTransportAlignment

class fmralign.alignment_methods.OptimalTransportAlignment(metric='euclidean', reg=1, tau=1.0, max_iter=1000, tol=0.001)

Compute the (unbalanced) optimal coupling between X and Y with entropic regularization using OTT-JAX as a backend for acceleration.

Parameters:

metricstr(optional)

metric used to create transport cost matrix, see full list in scipy.spatial.distance.cdist doc

regint (optional)

level of entropic regularization

taufloat (optional)

level of unbalancing, 1.0 corresponds to balanced transport, lower values will favor lower mass transport

Attributes:

Rjaxlib.xla_extension.Array

Mixing matrix containing the optimal permutation

__init__(metric='euclidean', reg=1, tau=1.0, max_iter=1000, tol=0.001)