ott.neural.methods.expectile_neural_dual.ENOTPotentials

class ott.neural.methods.expectile_neural_dual.ENOTPotentials(grad_f, g, *, cost_fn)

The dual potentials of the ENOT method [Buzun et al., 2024].

Parameters:

• grad_f (Callable[[Array], Array]) – Gradient of the first dual potential function.

• g (Callable[[Array], Array]) – The second dual potential function.

• cost_fn (TICost) – The cost function used to solve the OT problem.

Methods

distance(src, tgt)	Evaluate Wasserstein distance between samples using dual potentials.
plot_ot_map(source, target[, samples, ...])	Plot data and learned optimal transport map.
plot_potential([forward, quantile, ...])	Plot the potential.
transport(vec[, forward])	Transport vec according to Gangbo-McCann Brenier [Brenier, 1991].

Attributes

f
g
cost_fn