- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper studies how to learn Schrodinger bridges between distributions on Riemannian manifolds without simulating diffusion trajectories during training. The main difficulty is that Brownian transition densities and conditional bridge distributions generally do not have closed form expressions on Riemannian manifolds. To address this, the paper proposes SSR-FM, which uses an approximation of the Brownian transition density to construct a manifold transport cost. It then approximates conditional Brownian bridges using Gaussian distributions on minimizing geodesics, with covariance determined by the Hessian of the Brownian action. The authors theoretically justify these approximations when noise is small and show that the learned SDE recovers the marginals of the constructed probability path under ideal training and regularity assumptions. They evaluate SSR-FM on synthetic curved surfaces, geographic and molecular datasets on spheres and tori, and single cell datasets where the underlying data manifold is not known. SSR-FM generally achieves good results, although improvements over the strongest baselines are relatively small in several cases. The paper also provides ablations on the geometric covariance and endpoint coupling and shows substantially faster training than RDSB.
Critical strengths
- The paper proposes a framework for extending simulation-free Schrödinger bridge learning to Riemannian manifolds, where Brownian transition densities and conditional bridge distributions generally do not have closed-form expressions. The authors derive geometry aware transport costs and conditional Gaussian paths using approximations with small noise, and provide theoretical results that justify these constructions and show that the learned SDE recovers the constructed probability path under ideal conditions. These results provide theoretical motivation for the proposed method that is specific to Riemannian geometry.
- The method achieves competitive distribution matching while preserving manifold geometry. The authors also provide runtime comparisons showing that their method trains around 7 times faster than RDSB under similar update budgets.
Critical weaknesses
- The biggest weakness of the paper is that the improvements over existing methods are very marginal on most real-world datasets. Many of the absolute improvements are on the order of 10^-2 or 10^-3, while the W1 values themselves are on the order of 10^0 to 10^2, meaning that the relative improvements are often only a few tenths or hundredths of a percent. Also, the improvements are also often within standard deviation. For example, on NOAA, SSR-FM achieves compared to for RFM (0.04% improvement), and on IBTrACS, it achieves compared to for SF²M (0.10% improvement). The improvements in the single-cell experiments are similarly marginal. These results do not provide sufficient evidence that the proposed method offers meaningful advantages over existing methods, especially considering the additional geometric computations required over Riemannian flow matching methods.
- The paper could also benefit from testing on more complicated manifolds than the torus and sphere, such as SO(n) or U(n).
Questions for authors
See weakness
5 comments
Response to reviewer S8Bq(2/2)
W2
Weakness 2. Following the reviewer's suggestion, we have added experiments on , , and isometric embeddings. Table R9 reports the full comparison. These results are also presented in Section 6.2 of the revised manuscript (Figure 2 and Table 2), with experimental details in Appendix C.4 and additional trajectory visualizations in Appendix H.
Table R9. Hidden-time errors (), averaged over .
| Manifold family | Isometric embeddings | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Manifold | |||||||||||
| Intrinsic dimension | 10 | 45 | 105 | 496 | 25 | 100 | 225 | 1024 | 91 | 91 | 91 |
| Ambient dimension | 25 | 100 | 225 | 1024 | 50 | 200 | 450 | 2048 | 196 | 1000 | 10000 |
| OT-CFM | 0.545 | 1.086 | 1.444 | 2.036 | 0.805 | 1.586 | 2.037 | 2.902 | 1.296 | 1.305 | 1.365 |
| SF²M | 0.562 | 1.075 | 1.457 | 2.394 | 0.822 | 1.596 | 2.054 | 3.100 | 1.304 | 1.349 | 1.392 |
| Metric FM | 0.537 | 1.112 | 1.505 | 2.074 | 0.854 | 1.611 | 2.294 | 3.182 | 1.327 | 1.324 | 1.387 |
| RFM | |||||||||||
| RDSB | 0.635 | 1.410 | 2.053 | 4.879 | 1.425 | 2.225 | 3.102 | 4.578 | 1.725 | 2.232 | 2.849 |
| SSR-FM | 0.116 | 0.233 | 0.271 | 0.336 | 0.192 | 0.268 | 0.295 | 0.353 | 0.263 | 0.264 | 0.322 |
SSR-FM achieves the lowest among all compared methods across all eleven settings in Table R9, with an 87.1% reduction relative to RFM on . These results demonstrate a more pronounced advantage on complex, high-dimensional manifolds. The trajectory visualizations further show that SSR-FM more closely matches the reference process in its dominant transport branches and distributional spread (Figure 2 and Appendix H of the revised manuscript). We also evaluate isometric embeddings of in ambient dimensions 196, 1,000, and 10,000 while keeping its intrinsic dimension fixed at 91, with SSR-FM achieving the lowest in all three settings (Table R9; Table 2 in Section 6.2 of the revised manuscript).
Thank you for the constructive comments, which helped us present the evidence and limitations more clearly. We hope the revised paper better communicates the theoretical and algorithmic novelty of SSR-FM. We welcome additional questions or suggestions and will do our best to reply promptly after receiving them.
[1] Thornton, J., Hutchinson, M., Mathieu, E., De Bortoli, V., Teh, Y. W., & Doucet, A. (2022). Riemannian Diffusion Schrödinger Bridge. arXiv:2207.03024.
[2] Tong, A. Y., Malkin, N., Fatras, K., Atanackovic, L., Zhang, Y., Huguet, G., Wolf, G., & Bengio, Y. (2024). Simulation-Free Schrödinger Bridges via Score and Flow Matching. AISTATS, PMLR 238:1279–1287.
Brief follow-up to Reviewer S8Bq
Dear Reviewer S8Bq,
Before the discussion period ends on November 18, we would like to briefly follow up on your concerns about the practical advantages of our method. Our response discusses distributional accuracy, geometric adherence, and computational cost, alongside the newly added SO(n) and U(n) experiments. We would appreciate hearing whether this evidence addresses your concerns or whether further explanation would be useful. Thank you for your time and careful consideration.
Response to reviewer S8Bq(1/2)
We sincerely thank the reviewer for the careful assessment and constructive suggestions. We have expanded the evaluation to examine distributional accuracy, geometric adherence, and computational cost, and have added experiments on SO(n), U(n), and isometric embeddings. All additions and substantive revisions are highlighted in blue.
W1
Weakness 1. We appreciate the reviewer's concern about the practical gains. Among our baselines, only RDSB [1] targets the same Riemannian Schrödinger bridge problem, relying on iterative diffusion simulation during training, while SSR-FM addresses it by directly regressing the velocity and score fields. On the four real-world manifold tasks, SSR-FM (SDE) reduces W1 by 19.6%–75.6% relative to RDSB; it also achieves lower W1 on all six single-cell tasks, with a mean per-task relative reduction of 14.63% (Tables 3 and 4). Field training is also 7.08 times faster in the 200k-update EB100D benchmark (Appendix G.1). These results demonstrate substantial gains in both accuracy and training efficiency over an algorithm addressing the same class of Riemannian Schrödinger bridge problems.
Compared with SF²M, SSR-FM explicitly incorporates the manifold geometry into its reference diffusion and conditional paths. SF²M uses Euclidean Brownian bridge conditionals, which do not enforce manifold constraints and therefore do not guarantee that generated samples remain on the manifold. This lack of geometric control is one of the motivations for our work. In the original submission, we computed W1 in the common ambient Euclidean space to ensure a fair and transparent comparison across methods. Similar ambient W1 values may mask substantial off-manifold deviations in SF²M samples, so W1 alone does not fully capture the geometric advantages of SSR-FM. For example, under ODE sampling, SSR-FM reduces the mean distance to the manifold from 8.273 to 0.020 km on IBTrACS and from 6.744 to 0.004 km on NOAA. Under SDE sampling, the corresponding errors on ALA2 and Chignolin decrease from 0.074 and 0.763 to 0.000 at the reported precision (Table 3). Across all reported experiments where distance to a prescribed manifold can be measured, SSR-FM substantially reduces this error compared with SF²M (Tables 1–3; Appendix C.4).
Compared with RFM, SSR-FM has lower W1 on most evaluated tasks, while RFM's performance relative to other baselines is mixed across datasets (Tables 1–4). On the six single-cell tasks, SSR-FM achieves mean per-task relative W1 reductions of 1.75% (ODE) and 2.72% (SDE) over RFM, with both samplers outperforming RFM on four of the six tasks (Table 4). RFM remains competitive on NOAA. Similar behavior was reported in the original SF²M study [2], where SF²M and OT-CFM perform comparably on some datasets. Introducing stochasticity may provide limited gains for data dominated by deterministic motion. When biological processes exhibit substantial variability, modeling stochastic fluctuations can be important. Our biological benchmarks include clearer improvements over RFM: SSR-FM (SDE) reduces W1 by 11.2% on EB (10D) and 15.7% on Chignolin (Tables 3 and 4), supporting its value for modeling biological populations and molecular configurations.
Overall, we derive a simulation-free algorithm for approximating Schrödinger bridges on Riemannian manifolds from a common Riemannian Brownian reference, providing a capability missing from the prior methods compared in Appendix A.