- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates Wasserstein gradient flows for particle sampling and provides a new interpretation of LAWGD's preconditioning mechanism from the perspective of second-order Wasserstein geometry. This paper further proposes a framework for directly learning the transport operator with two finite-sample implementations based on kernels and neural networks. The convergence properties of the approximate transport dynamics and the representational limitations of fixed kernels in high-dimensional settings are analyzed in the paper. Experiments on synthetic distributions, stochastic physical systems, and molecular dynamics data demonstrates the effectiveness of the proposed methods.
Critical strengths
- This paper provides a geometric interpretation of LAWGD, which is insightful. Besides, the theoretical analysis is generally well-motivated and clearly presented.
- This paper develops both kernel and neural implementations of the proposed approach, supported by theoretical analysis and experiments across different settings. Experimental results demonstrate some promising improvements.
Critical weaknesses
- The proposed method requires access to samples from the target distribution, which raises questions about its practical necessity as sampling algorithms. While this assumption may be reasonable in certain generative modeling settings, this paper does not sufficiently justify why learning a transport operator and performing iterative particle updates would be preferable to directly training generative models on the available samples. Moreover, the improvements in sampling quality are relatively modest outside the synthetic Gaussian experiments, and comparisons with existing generative models are missing. These limitations make the practical advantages of the proposed approach unclear.
- The convergence analysis does not directly cover the practical finite-sample algorithms. Besides, experiments provide limited evidence of how these theoretical results translate into actual convergence behavior and sampling performance.
Questions for authors
- How sensitive is the proposed method to the number of target samples, the transport rank, and particle initialization?
- How do the assumptions underlying Theorem 3 relate to the practical finite-sample learning algorithms?
- What are the computational complexities of the proposed kernel and neural methods, considering both operator learning and iterative particle sampling?
We thank the reviewer for their constructive comments.
1. Why learn from target samples, rather than train a generative model directly?
As the reviewer pointed out, our setting is generative modeling from a finite dataset: the goal is to transport fresh source particles toward the target distribution represented by those data. This follows the sample-based particle-flow setting of MMD flow (Arbel et al., 2019), KALE (Glaser et al., 2021), and DrMMD (Chen et al., 2025). Our contribution provides a principled way to learn inverse-generator preconditioning and study how its approximation affects particle motion. The operator is fitted once and reused during sampling.
To test sampling beyond Gaussian targets, we added a smoothed version of DrMMD’s three-ring experiment, where particles start in a compact cloud and must spread across all three rings while recovering their masses and thickness. Across five random seeds, K-T achieves a mean energy distance of 3.3×10−4, comapred with 2.5×10−4 for DrMMD. The two methods also produce rings of similar thickness, approximately 0.05, matching the target’s radial spread..
2. Relationship between Theorem 3 and the practical algorithms.
Theorem 3 provides sufficient conditions for contraction of the population flow. Its purpose is to identify the properties an approximate transport operator must satisfy; we are not claiming that it certifies the particular operators obtained by our finite-sample training procedure. The revised manuscript makes this distinction explicit in Section 3.3 and clarifies the connection between the population learning objective and the ideal truncated operator in Section 4.2.
3. Sensitivity to sample size, rank, and initialization.
Target samples: The reported comparisons use fixed sample banks: 200,000 target samples per dimension in the Gaussian experiment and 10,000 in the rings experiment. These data determine both the learned functions and their target averages; the relevant consideration is coverage as well as sample count.
Transport rank: The Gaussian benchmark uses rank five to approximate its two linear and three quadratic slow modes. The rings experiment uses higher ranks, including a maximum requested rank of 128 for K-T. We specify the kernel settings and actual retained ranks, since increasing the requested rank is useful only when additional functions can be estimated reliably.
Initialization: A distant initialization can encounter very small kernel gradients or inaccurate neural extrapolation. The rings comparison uses the same compact initial cloud for every method.
4. Computational complexity and total cost.
For n target samples, m dictionary features, and dimension d, forming the full covariance and Dirichlet matrices and solving the generalized eigenvalue problem costs O(ndm2+m3), assuming each kernel value and gradient costs O(d) to evaluate. Once a rank-r model is fitted, one velocity evaluation on P particles costs O(P(dm+mr)+mr).
For neural fitting, let U denote the number of outer updates, b the minibatch size, r the rank, and KH and KA the numbers of forward and adjoint response updates per outer update. The training cost is
O(Ub[CF+KHCH+KACA+dr2]).
Here, CF, CH, and CA are the per-sample network-computation costs for factor and response updates, including the required automatic differentiation and frozen-network evaluations. The dr2 term accounts for the factor Gram matrices. These costs depend on network architecture and rank.
For P particles and S velocity evaluations, neural sampling costs
O(SP[Cg+Cb+dr]).
Here, Cg and Cb include evaluation of the calibrated scalar and vector factors. Auxiliary response optimization occurs during training only. Calibration contributes an additional one-time cost.
Once fitted, both methods evaluate particle velocities at a cost linear in the number of particles. We can reuse the fitted operator for further sampling runs with the same target, without repeating the training. We have added these complexity expressions to Appendix D.