ott.solvers.quadratic.lower_bound.LowerBoundSolver

Contents

ott.solvers.quadratic.lower_bound.LowerBoundSolver#

class ott.solvers.quadratic.lower_bound.LowerBoundSolver(epsilon=None, distrib_cost=None)[source]#

Lower bound OT solver.

Computes the third lower bound distance from [Mémoli, 2011], def. 6.3.

Parameters:
  • epsilon (Optional[float]) – Entropy regularization for the resulting linear problem.

  • distrib_cost (Optional[UnivariateWasserstein]) – Univariate Wasserstein cost, used to compare two point clouds in different spaces, where each point is seen as its distribution of costs to other points in its point cloud.

Methods