
CFM introduces efficient training objectives for CNFs, improving generative modeling tasks.


coremsg

flow-based-generative-models-with-minibatch-optimal-transport


Flow-Based Generative Models with Minibatch Optimal Transport


title_rewrite


Continuous normalizing flows (CNFs) are a generative method for learning probability distributions from finite random samples. This work establishes non-asymptotic error bounds for the distribution estimator based on CNFs with linear interpolation and flow matching, under assumptions on the target distribution.


theoretical-analysis-of-continuous-normalizing-flows-for-learning-probability-distributions


Theoretical Analysis of Continuous Normalizing Flows for Learning Probability Distributions
