Ctrl+K

ott.neural.methods.flows.dynamics.BrownianBridge

Contents

ott.neural.methods.flows.dynamics.BrownianBridge#

class ott.neural.methods.flows.dynamics.BrownianBridge(sigma)[source]#

Brownian Bridge.

Sampler for sampling noise implicitly defined by a Schrödinger Bridge problem with parameter \(\sigma\) such that \(\sigma_t = \sigma \cdot \sqrt{t \cdot (1 - t)}\) [Tong et al., 2023].

Parameters:

sigma (float) – Noise used for computing time-dependent noise schedule.

Methods

compute_mu_t(t, src, tgt)

Compute the mean of the probability path.

compute_sigma_t(t)

Compute noise of the flow at time \(t\).

compute_ut(t, src, tgt)

Evaluate the conditional vector field.

compute_xt(rng, t, src, tgt)

Sample from the probability path.
Contents