Convergence Analysis of Flow Matching in Latent Space with Transformers
pith:TOVLGTF2open to challenge →
read the original abstract
We present theoretical convergence guarantees for ODE-based generative models, specifically flow matching. We use a pre-trained autoencoder network to map high-dimensional original inputs to a low-dimensional latent space, where a transformer network is trained to predict the velocity field of the transformation from a standard normal distribution to the target latent distribution. Our error analysis demonstrates the effectiveness of this approach, showing that the distribution of samples generated via estimated ODE flow converges to the target distribution in the Wasserstein-2 distance under mild and practical assumptions. Furthermore, we show that arbitrary smooth functions can be effectively approximated by transformer networks with Lipschitz continuity, which may be of independent interest.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Approximation Error Upper and Lower Bounds for H\"{o}lder Class with Transformers
A standard Transformer with O(ε^{-d0/α}) blocks can approximate any bounded d0-dimensional Hölder function of smoothness α to accuracy ε, but at least Ω(ε^{-d0/(4α)}) blocks are required.
-
Approximation Error Upper and Lower Bounds for H\"{o}lder Class with Transformers
Transformers require Ω(ε^{-d0/(4α)}) to O(ε^{-d0/α}) blocks to approximate bounded d0-dimensional Hölder-α functions to accuracy ε.
-
Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
A conditional flow matching model generates realistic safety-critical traffic scenarios by turning nominal scenes into dangerous rollouts using combined simulation and real data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.