- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studied sampling guarantee of Riemannian diffusion models. Existing works only proved polynomial guarantee, but didn't explicitly work out the specific order. This paper tried to gave specific order.
Critical strengths
Personally I think this is a very interesting problem. In the sampling literature, to the best of my knwledge, analyzing the manifold Brownian motion simulation error (e.g., geodesic random walk) is a difficult, and the only existing result is a Wasserstein analysis under synchronous coupling. Recent paper Xu et al. (2026) proved polynomial guarantee, but the specific order is still open in KL or TV.
Possibly a question that might be out of the scope of the submitted paper could be, to trace the order of Wasserstein error bound of geodesic random walk (As I recall it might be like but I am not sure) in Cheng et al. (2022) and compare with the error bound in this paper. Just a comparison on manifold Brownian motion simulation itself.
Critical weaknesses
The main text is well written and easy to follow, but I feel some parts of the appendix difficult to follow. I think a revision on Appendix is needed.
Questions for authors
Some questions:
I feel Appendix D contain some typos and is difficult to follow.
Appendix D.4.1 ANALYSING THE DENSITY RATIO: for example, around line 1500, I don't see how the inequality was obtained. The rest of this subsection is also difficult to follow for me.
line 1481-1482: I didn't find where the author discuss the required range of . I think should be upper bounded by something depending on , and this is important.
As this is not the first convergence proof on Riemannian diffusion model, I think it's better to avoid using and notation through the proof, and only use it when it comes to the conclusion/final order. Moreover, I noticed that a universal constant C was used throughout the proof. I think it's better to define constants separately and track them (I feel this might make the proof easier to follow).
Line 448, "for sufficiently small " I think this should be stated explicit (e.g., require or so). I am not saying such condition is not ok. I understand manifold Brownian motion is complicated and difficult to analyze. But as I see from the proof (if I am wrong please let me know) the small epsilon played a role, in some sense absorbed some extra dimension dependency. What I mean is, back to the proof of Xu et al. (2026), they imposed some upper bound (say, ) on time interval of Brownian motion simulation. And in the submitted paper I think the author also imposed a similar condition. Now if this upper bound on the time variable which control the maximal allowed Brownian motion simulation time, has a very bad dependency on some variables, e.g. or even , the required small would need to carry such order, to make small (so that the condition is satisfied).
possible typo: line 1228, clipped or truncated?
Summary: interesting paper, but the proof need more polishing, and track the constants more carefully.
7 comments
Response
Thank the author for the response. I think there might be some other typos, and I strongly encourage the author to check them. I think some typos, after correction, would also affect other parts of the proof so a more careful check is needed. I'm willing to raise my score if these can be addressed.
Line 1522, the equation, if I expect the integral of to be 1, should there be an indicator function?
Line 1557, the equation, should it be or ?
The equation around line 1610, if I take , I get .
Line 1603, I think the author plug in but the sign might be a typo? I mean maybe it should be something like .
Line 1708, the expression of , the seems to be a typo. (also the term?)
Thank you very much for your suggestions. We have corrected the typos you pointed out and also carefully checked the remaining parts of the proof, making further corrections to typos in Appendices B and D. We hope these revisions address your concerns.
Thank you for your time and effort in reviewing our paper! We are grateful for your constructive suggestions, which have significantly guided our improvements. Please find our responses to your comments below.
A: Thank you for your suggestion. We have expanded the derivation of the inequality and provided additional explanations to make the proof easier to follow. In particular, for the inequality you are asking, we now explicitly write the derivation as Q(t,x,y)P^(t,x,y)−1≤q^t(x,y)u0(x,y)P^(t,x,y)−1+q^t(x,y)u0(x,y)P^(t,x,y)−qt(x,y)u0(x,y)j(x)−1P^(t,x,y)+qt(x,y)u0(x,y)j(x)−1P^(t,x,y)−Q(t,x,y)P^(t,x,y) ≤q^t(x,y)u0(x,y)P^(t,x,y)−1+q^t(x,y)u0(x,y)P^(t,x,y)⋅qt(x,y)j(x)−1q^t(x,y)−1+qt(x,y)u0(x,y)j(x)−1P^(t,x,y)⋅Q(t,x,y)qt(x,y)u0(x,y)j(x)−1−1. Here, the fractions q^t(x,y)u0(x,y)P^(t,x,y) and qt(x,y)u0(x,y)j(x)−1P^(t,x,y) are close to 1 (because all the absolute values on the right hand side are small), and are therefore upper bounded by constants.
We hope these revisions address your concerns.
A: Thank you for pointing this out. In the revised version, we have explicitly summarized the required conditions on the step sizes in Theorem 5.3, which is h′≤cmin{d−9T−1log−1(d),d−4δ2,d−3δ3}. In particular, this leads to ϵ≤min{d−5/2log1/2d,δ1/2d−1/2} in Corollary 5.4 to make sure the complexity bound is valid.
A: Thank you for your suggestion. In the revised version, we use separately numbered constants (e.g., C1,C2) within each section to make the derivations easier to follow. At the end of each section, we summarize the corresponding results using a universal constant C, making the main conclusions of each separate section clearer. Moreover, we now avoid using o and O notations during the proof, particularly for the derivation of bounding u1,∇u1 and Δu1. In the revised version, o and O are only used for a brief view of the bounds. We hope these revisions address your concerns.
A: Thank you for your suggestion. In the revised version, we have explicitly stated the conditions on ϵ required to ensure that the corresponding step size h′ is sufficiently small. In our revised Corollary 5.4, the condition for the (simplified) score-evaluation complexity is ϵ≤d−1T−1, and the condition for GRW complexity is ϵ≤min{d−5/2log1/2d,δ1/2d−1/2}.
A: It should be "truncated". Thank you for pointing out this typo, and it is now revised.
We hope our response addresses your concerns. If so, we wonder if you could kindly consider raising your score? We will also be happy to answer any further questions you may have. Thank you very much!