Flow-based generative model: Difference between revisions

Revision as of 11:14, 18 July 2022

Revision as of 11:17, 18 July 2022

Line 149:

To regularize the flow <math>f</math>, one can impose regularization losses on <math>\nabla_z f(z, t)</math>. The paper <ref name="Finlay 3154–3164"/> proposed the following regularization loss based on [[Optimal transport|optimal transport theory]]:<math display="block">\lambda_{K} \int_{0}^{T}\left\|f(z_t, t)\right\|^{2} dt

+\lambda_{J} \lambda_{K} \int_{0}^{T}\left\|\nabla_z f(z_t, t)\right\|_F^{2} dt

</math>where <math>\lambda_K, \lambda_J >0

</math>

</math> are hyperparameters. The first term punishes the model for varying the flow field over time, and the second term punishes it for varying the flow field over space.

== Applications ==