ott.problems.linear.semidiscrete_linear_problem.SemidiscreteLinearProblem#

class ott.problems.linear.semidiscrete_linear_problem.SemidiscreteLinearProblem(geom, b=None, tau_b=1.0)[source]#

Semidiscrete linear OT problem.

Instances of this problem can be sampled using the sample() method.

Parameters:

geom (SemidiscretePointCloud) – Semidiscrete point cloud geometry.
b (Optional[Array]) – The second marginal. If None, it will be uniform.
tau_b (float) – If \(< 1\), defines how much unbalanced the problem is on the second marginal. Currently not implemented.

Methods

`potential_fn_from_dual_vec`(g, *[, epsilon])	Get potential function from a dual vector using the c-transform.
`sample`(rng, num_samples, *[, epsilon])	Sample a linear OT problem.

Attributes

`b`	Second marginal.
`epsilon`	Entropic regularization.

ott.problems.linear.semidiscrete_linear_problem.SemidiscreteLinearProblem