- class ott.problems.linear.potentials.DualPotentials(f, g, *, cost_fn, corr=False)[source]#
The Kantorovich dual potential functions \(f\) and \(g\).
\(f\) and \(g\) are a pair of functions, candidates for the dual OT Kantorovich problem, supposedly optimal for a given pair of measures.
float]) – The first dual potential function.
float]) – The second dual potential function.
CostFn) – The cost function used to solve the OT problem.
bool) – Whether the duals solve the problem in distance form, or correlation form (as used for instance for ICNNs, see, e.g., top right of p.3 in [Makkuva et al., 2020])
Evaluate 2-Wasserstein distance between samples using dual potentials.
plot_ot_map(source, target[, forward, ax, ...])
Plot data and learned optimal transport map.
plot_potential([forward, quantile, ax, ...])
Plot the potential.
vecaccording to Brenier formula [Brenier, 1991].
The first dual potential function.
The second dual potential function.