# A Theoretical Analysis of Discrete Flow Matching Generative Models

arXiv: https://arxiv.org/abs/2509.22623 · HTML: https://mlsanity.com/paper/2509.22623/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design](https://mlsanity.com/paper/2402.04997/) (2024)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [Continuous diffusion for categorical data](https://mlsanity.com/paper/2211.15089/) (2022)
- [Error Bounds for Flow Matching Methods](https://mlsanity.com/paper/2305.16860/) (2023)
- [DeFoG: Discrete Flow Matching for Graph Generation](https://mlsanity.com/paper/2410.04263/) (2024)
- [Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory](https://mlsanity.com/paper/2403.11968/) (2024)
- [Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?](https://mlsanity.com/paper/2307.14023/) (2023)
- [How Smooth Is Attention?](https://mlsanity.com/paper/2312.14820/) (2023)
- [Flow matching achieves almost minimax optimal convergence](https://mlsanity.com/paper/2405.20879/) (2024)
- [Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency](https://mlsanity.com/paper/2411.16525/) (2024)
- [On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality](https://mlsanity.com/paper/2411.17522/) (2024)
- [Convergence Analysis of Flow Matching in Latent Space with Transformers](https://mlsanity.com/paper/2404.02538/) (2024)
- [MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation](https://mlsanity.com/paper/2502.11234/) (2025)
- [[MASK] is All You Need](https://mlsanity.com/paper/2412.06787/) (2024)
- [All-atom inverse protein folding through discrete flow matching](https://mlsanity.com/paper/2507.14156/) (2025)

## Built on by (most cited first, 14 of 14)

- [WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving](https://mlsanity.com/paper/2512.06112/) (2025)
- [Flow Matching is Adaptive to Manifold Structures](https://mlsanity.com/paper/2602.22486/) (2026)
- [On Flow Matching KL Divergence](https://mlsanity.com/paper/2511.05480/) (2025)
- [Flow Matching for Offline Reinforcement Learning with Discrete Actions](https://mlsanity.com/paper/2602.06138/) (2026)
- [Dimension-free error estimate for diffusion model and optimal scheduling](https://mlsanity.com/paper/2512.01820/) (2025)
- [Corrected Samplers for Discrete Flow Models](https://mlsanity.com/paper/2601.22519/) (2026)
- [Discrete Flow Matching Policy Optimization](https://mlsanity.com/paper/2604.06491/) (2026)
- [Minimax Optimality of Score-Entropy Discrete Diffusion](https://mlsanity.com/paper/2608.20635/) (2026)
- [Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions](https://mlsanity.com/paper/2605.08882/) (2026)
- [A Theory on Flow Matching with Neural Networks](https://mlsanity.com/paper/2606.10089/) (2026)
- [SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation](https://mlsanity.com/paper/2606.11969/) (2026)
- [Transformer Approximations from ReLUs](https://mlsanity.com/paper/2604.24878/) (2026)
- [A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching](https://mlsanity.com/paper/2606.24140/) (2026)
- [Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry Perspective](https://mlsanity.com/paper/2609.06947/) (2026)

## Abstract (arXiv)

We provide a theoretical analysis for end-to-end training Discrete Flow Matching (DFM) generative models. DFM is a promising discrete generative modeling framework that learns the underlying generative dynamics by training a neural network to approximate the transformative velocity field. Our analysis establishes a clear chain of guarantees by decomposing the final distribution estimation error. We first prove that the total variation distance between the generated and target distributions is controlled by the risk of the learned velocity field. We then bound this risk by analyzing its two primary sources: (i) Approximation Error, where we quantify the capacity of the Transformer architecture to represent the true velocity, and (ii) Estimation Error, where we derive statistical convergence rates that bound the error from training on a finite dataset. By composing these results, we provide the first formal proof that the distribution generated by a trained DFM model provably converges to the true data distribution as the training set size increases.