- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper designs a new source (noise) distribution for flow matching (FM) that adapts to the data distribution. The goal is to show that FM using this new source outperforms the standard choice (i.e., normal centered with unit variance) and the other source constructions recently proposed in the literature. The proposed approach consists in splitting the ambiant space into neighborhoods chosen according to data points, and then choosing a Gaussian Mixture noise distribution. In this GMM, the covariance of each mode is estimated with a truncated PCA on the corresponding neighborhood of the data, and the weights of the mixture are defined with the density of data points. The novelty compared to previous work is to adapt the source noise locally in space (i.e., the PCA part).
Critical strengths
- The idea is simple to follow
- The numerical results are reasonably good
- The numerical cost of the method to estimate the source is probably not very high
Critical weaknesses
- The contribution is limited: there are a lot of papers in the literature that try (with more or less success) to design a better source noise. The use of both anisotropic Gaussian noise whose covariance captures the local geometry of the data manifold, and of isotropic GMMs is already in the literature. The novelty here is, in a nutshell, to mix the two ideas.
- There are lots of hyperparameters to this source design. In my opinion, there is a low probability that it will be adopted in practice in some future works.
Questions for authors
Main questions
-
About the theoretical claims (l. 216 and Remark 1): I had trouble to follow what you wanted to say. First, what exactly would be the goal of establishing this bound / what does it tell about your method? Secondly, I could not understand several notation, please fix them and clarify the statements: are and the same? What does mean? (l 247). Did you mean ? Similarly, what is here compared to ? Also an orthogonal projector is always 1-Lipschitz, so why do you need to make that assumption?
-
I find there is a contradiction between the known fact that having a source distribution too close to the data distribution is usually harmful [1], and the fact that your approach is exactly trying to fit at the best the source on the data. Actually, from Figure 1, we see that your source is very similar to the data. What in your opinion explains this apparent contradiction? Is it only due to the isotropy added via ? How does your method behave when ?
-
Section 3.3: why not use the Voronoi cells as neighborhoods. What happens if you do? Could you also reexplain the difference between the final neighborhood and the Voronoi cells.
-
In the appendix, you say you use both independent and Hungarian coupling (which I guess here is exactly the minibatch OT coupling) while for instance you use independent coupling for Adapting Noise baseline. The latter was initially proposed with the minibatch OT coupling. For fairness, could you compare all methods for independant and minibatch OT, for instance of MNIST?
-
Coud you scale to a bigger image dataset (Cifar10, Celeba64...)?
-
Is it necessary that the source has zero mean or the method could work without recentering (i.e., )?
-
Does the proposed method improve over standard FM for unimodal (1-class) data?
Minor remarks
- The first sentence of the abstract is not clear, we don't understand what the spatially varying subspace refer to. In general, both with the abstract and introduction, it took me time to understand what you meant by subspaces even though I know the topic. Consider revising the paper for reaching a broader audience.
- When introducing FM, [3] should also be cited.
- The reference [2] is missing
[1] : Lee, Kwanseok Kim, and Joonseok Lee. Is there a better source distribution than gaussian? Exploring source distributions for image flow matching. Transactions on Machine Learning Research, 2026
[2] Luo, Gaoxiang and Cole, Frank and Zhang, Sihang and Wan, Yuxiang and Lu, Yulong and Sun, Ju, Flow Matching for Multimodal Distributions, CVPR 2026
[3] Albergo, Michael S. and Vanden-Eijnden, Eric, Building normalizing flows with stochastic interpolants, ICLR 2023