Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
By: Mudit Gaur , Prashant Trivedi , Shuchin Aeron and more
Potential Business Impact:
Makes AI create better pictures with less data.
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing empirical success, the theoretical understanding of flow matching remains limited, particularly in terms of sample complexity results. In this work, we provide the first analysis of the sample complexity for flow-matching based generative models without assuming access to the empirical risk minimizer (ERM) of the loss function for estimating the velocity field. Under standard assumptions on the loss function for velocity field estimation and boundedness of the data distribution, we show that a sufficiently expressive neural network can learn a velocity field such that with $\mathcal{O}(ε^{-4})$ samples, such that the Wasserstein-2 distance between the learned and the true distribution is less than $\mathcal{O}(ε)$. The key technical idea is to decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field. Each of these terms are then handled via techniques that may be of independent interest.
Similar Papers
Distribution estimation via Flow Matching with Lipschitz guarantees
Machine Learning (Stat)
Makes AI learn faster and better.
Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware
Machine Learning (CS)
Makes AI create pictures much faster on phones.
Provable Mixed-Noise Learning with Flow-Matching
Machine Learning (CS)
Fixes messy data from science experiments.