- Rating
- 4(+1)
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes LatentFlow, a general method for conditional sampling from stochastic processes. A deterministic map (generator) from the latent space to the process space is used to pull back the conditioning likelihood to the latent space, and the resulting latent posterior is sampled using a guided reverse-time SDE based on a variance-preserving Gaussian noising bridge. The method is evaluated across a diverse set of stochastic-process conditioning tasks, with experiments examining its flexibility, sampling accuracy, and computational efficiency.
Critical strengths
- Featuring its mild latent-representation assumption and a unified construction, this method is applicable to a wide range of processes and even extends to inference over unknown model parameters.
- The training-free nature and relatively low computational requirements make the method promising for realistic simulation and inference scenarios.
Critical weaknesses
- The sampling procedure appears closely related to that of FlowGP. The main contribution therefore seems to be the extension and unification of the framework rather than a fundamentally new sampling algorithm.
- The scope of the claims about sampling within seconds and controllable error is not fully clear, since the practical performance depends on hyperparameters such as , the integration step size, and the latent dimension, as well as on the regularity and computational properties of the generator that cannot be guaranteed in all cases.
Questions for authors
Please refer to Weaknesses.
3 comments
Response to uWJL [Part 2/2]
W2 (scope of claims). We thank the reviewer for raising this point, and agree that our original claims regarding "sampling in seconds" and "controllable error" were not sufficiently precise. We have now revised these claims, and added theoretical and empirical results which clarify how they depend on the hyperparameters, the latent dimension, and the properties of the generator.
- Computational cost. Each draw requires evaluations of the generator and its gradient, where is the number of integration steps and is the number of MC samples. The cost thus depends on the latent dimension only through the cost of a single evaluation of the generator. We have removed the claim of "sampling in seconds" from the abstract and the introduction, and Sec. 1 now states this cost instead. We also now provide a comprehensive wall-clock comparison (App. I.5), which measures the time taken by LatentFlow and a range of alternative methods to reach the "exact-sample floor" (the error attained by the same number of exact posterior samples) on 46 problems.
- Approximation error. The error of LatentFlow decomposes into three terms: terminal initialisation, MC guidance, and time discretisation (Sec. 3, App. D). The terminal error depends only on the terminal noise level (Thm. D.11), and the discretisation error decreases with (Cor. D.5), reaching the floor for moderate with our default schedule and time grid (App. I.1). Meanwhile, the MC guidance error is bounded by (Thm. D.11), where bounds the gradient of the pulled-back log-likelihood, and accumulates along the flow a quantity which measures how strongly the condition reweights the bridge draws. Increasing thus reduces this error when . Meanwhile, we can use the ESS of the guidance weights to indicate when this is not the case (App. I.2).
- Latent dimension. The difficulty of estimating the guidance depends not on the full latent dimension, but on the number and the sharpness of the directions constrained by the condition (Cor. D.9, Prop. D.10). For example, Fig. 7 shows spatio-temporal examples with up to 122K latent dimensions, conditioned on events which constrain only a few directions. We now discuss this in Sec. 6, along with the regimes in which LatentFlow is expected to perform well (e.g., weakly informative conditions, constraints acting on few directions) or less well (e.g., many sharply constrained directions, non-affine generators), as illustrated in App. I.3.
- Regularity of the generator. Our bounds in the process space require to be Lipschitz on the region visited by the sampler (Cor. D.7), and gradient-based guidance also requires differentiability. We now state clearly in Sec. 6 that hard constraints, discontinuous simulators, and non-smooth generators may require relaxations, surrogates, or derivative-free guidance (App. E.1), for which our theoretical guarantees are more limited.
Thank you for the detailed response. I believe the reply and the revisions have addressed my concerns, and I have raised my score from 3 to 4.
Response to uWJL [Part 1/2]
Many thanks for your time in reviewing this paper, and for your helpful feedback. We are glad to hear that you found the paper interesting. We provide detailed responses to each of your comments below. In brief: in Sec. 4 we now make clearer the relationship between LatentFlow and FlowGP [1], and the specific contributions of this work. We have also made our claims regarding the computational cost and the approximation error more precise throughout the paper, and now support these with new theoretical results (App. D.3) and a comprehensive wall-clock comparison on 46 problems (App. I.5).
W1 (relation to FlowGP). We agree with the reviewer that LatentFlow is closely related to FlowGP. In particular, when the generator is affine, Tϑ(ξ)=m+Lξ, and the posterior is sampled using the probability-flow ODE, LatentFlow reduces to FlowGP. We now state this explicitly in Sec. 4. We also agree that our main contribution is the extension and unification of this framework, rather than a fundamentally new sampling algorithm. We would argue, however, that this extension is still substantive:
References
[1] Moss, H. B., et al. (2026). Conditioning Gaussian processes on almost anything. arXiv:2605.21041.