ott.neural.methods

Flow Matching

flow_matching.flow_matching_step(model, ...)	Perform a flow matching step.
flow_matching.interpolate_samples(rng, x0, x1)	Sample time and interpolate.
flow_matching.evaluate_velocity_field(model, x)	Solve an ODE.
flow_matching.curvature(model, x0[, cond, ...])	Compute the curvature [Lee et al., 2023].
flow_matching.gaussian_nll(model, x1[, ...])	Compute the Gaussian negative log-likelihood.

Monge Gap

monge_gap.monge_gap(map_fn, reference_points)	Monge gap regularizer [Uscidda and Cuturi, 2023].
monge_gap.monge_gap_from_samples(source, target)	Monge gap, instantiated in terms of samples before / after applying map.
monge_gap.MongeGapEstimator(dim_data, model)	Mapping estimator between probability measures.

Neural Dual

neuraldual.W2NeuralDual(dim_data[, ...])	Solver for the Wasserstein-2 Kantorovich dual between Euclidean spaces.
expectile_neural_dual.ExpectileNeuralDual(...)	Expectile-regularized Neural Optimal Transport (ENOT) [Buzun et al., 2024].
expectile_neural_dual.ENOTPotentials(grad_f, ...)	The dual potentials of the ENOT method [Buzun et al., 2024].