- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes PhiBE-Flow, a framework for learning continuous-time probability velocity fields from discrete observations of stochastic dynamical systems. By combining PhiBE approximations with the Fokker–Planck equation, the authors derive a variational objective that avoids explicit estimation of SDE coefficients and density scores. The paper provides theoretical convergence guarantees for time-discretization and finite-sample errors. Experiments on stochastic dynamical systems, Navier–Stokes equations, and video generation demonstrate the effectiveness of the proposed method, with improved performance over representative baselines on high-dimensional generation tasks.
Critical strengths
-
The paper presents a well-motivated learning formulation that combines the Fokker–Planck equation, PhiBE approximations, and integration by parts to directly learn probability velocity fields without requiring known SDE coefficients or explicit score estimation.
-
The experiments cover a diverse range of stochastic systems and demonstrate promising performance, particularly on Navier–Stokes dynamics and video generation.
Critical weaknesses
-
The paper lacks ablation studies to validate the contributions of its key components. In particular, the role of the Jacobian term in the proposed objective is not isolated, making it difficult to assess its importance in capturing stochastic diffusion effects.
-
The experimental comparisons are limited to representative generative baselines. Comparisons with methods that explicitly estimate SDE drift and diffusion coefficients or learn probability flows through score estimation would provide stronger evidence for the advantages of the proposed direct learning approach.
Questions for authors
-
Could the authors provide an ablation study removing the Jacobian term and comparing against direct drift regression to clarify its contribution to learning the probability velocity field?
-
Could the authors include comparisons with approaches that first estimate SDE coefficients or density scores and then construct the corresponding probability flow, under matched experimental settings?
3 comments
Thank you for the helpful response. My main concerns have been addressed, and I am raising my score to 3.
We sincerely thank you for your constructive feedback and careful consideration.
We thank the reviewer for the careful reading and constructive suggestions. We address the two questions below.
1. Ablation of the Jacobian term
We added a controlled ablation on both reversible and non-reversible OU examples, comparing the full PhiBE-Flow objective with ordinary increment regression using the same five-layer, width-50 MLP. The latter removes the Jacobian term and minimizes
Ldrift(θ)=Nx(Nt−1)1∑k=1Nx∑i=0Nt−2vθ(xti(k),ti)−Δtxti+1(k)−xti(k)22.
For the reversible/non-reversible cases, the full objective reduces:
Affine-model ablations, obtained by setting C=0, show consistent improvements. These results support the importance of the Jacobian term for recovering probability velocities and marginal distributions.
The Fig. 9 in our revised manuscript compares analytical probability-flow trajectories with drift-only MLP and affine rollouts. The drift-only models fail to preserve the correct ensemble spread, illustrating the effect of omitting the Jacobian correction.
These reduced-scale experiments use T=1, 2,048 trajectories, 201 observation times, an 80/20 trajectory-level split, and one seed. Velocity and path errors are evaluated against the analytical OU probability velocity and probability-flow trajectories, respectively.
In the revised manuscript, we report the MLP ablation in Section 5.1 and the experimental details in Appendix B.2.
2. Comparison with separate SDE-coefficient and score estimation
We compare PhiBE-Flow with a two-stage approach that estimates the drift and diffusion coefficients, learns the marginal score using denoising score matching (DSM), and then constructs the probability velocity.
To test this comparison in higher dimension, we considered 12-dimensional OU systems with rotational-coupling strengths 0, 2, and 5, corresponding to reversible, non-reversible, and stronger-rotation cases. For each setting, we used 512 trajectories (409 for training), 51 observation times on [0,1], and 12 paired data seeds with fixed SDE coefficients.
We compared the time-indexed affine PhiBE field with a two-stage estimator using pooled affine drift regression, residual-based diffusion estimation, and a time-indexed affine score trained with the DSM loss (Song et al., 2021), with σdsm=0.05. Both methods use the same training trajectories.
As shown in the Fig. 10 in our revised manuscrips, the time-averaged Gaussian W2/d errors, averaged over seeds, were:
PhiBE had lower error in all 12 paired seeds in each setting. These results provide evidence that, in the tested high-dimensional affine OU settings, jointly learning the probability velocity can reduce errors accumulated by this separate coefficient-and-DSM-score pipeline.
This comparison also highlights a limitation of identifying continuous-time SDE coefficients from discrete observations. Consider two linear SDEs with drifts
b0(x)=−x,b1(x)=(−I+h2πJ)x,J=01−10,
and the same isotropic diffusion loading σI. At observation interval h, both induce exactly the same transition kernel,
Ph(⋅∣x)=N!(e−hx,,2σ2(1−e−2h)I),
despite having different intermediate-time dynamics. Thus, even perfect knowledge of the sampled transitions does not uniquely identify the continuous-time SDE.
PhiBE-Flow does not require SDE coefficient identification as an intermediate step: it directly estimates a finite-step approximation to the probability velocity through its variational objective. For the non-rotating OU system with a centered Gaussian marginal, minimizing the full objective over linear velocity fields gives
vh=αhv⋆,αh=2h1−e−2h=1−h+O(h2),
making the finite-step approximation bias explicit without selecting an SDE-generator branch.
In the revised manuscript, we add these evaluations and their experimental settings to Appendix B.8, with a brief reference at the end of the OU experiment subsection.
References
Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations, 2021. Paper.