- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates probabilistic forecasting under partial observation, comparing direct stochastic interpolants (Direct SI), which learn the conditional distribution between initial and final states, with cascaded stochastic interpolants (Cascaded SI), which learn shorter transitions and compose them to obtain the final forecast.
The authors introduce a benchmark involving five physical systems, where multiple trajectories are generated from the same observed initial condition by varying the unobserved components. This allows the quality of the learned conditional distributions to be evaluated against reference ensembles obtained from numerical simulations.
The experimental results show that Cascaded SI significantly improves conditional forecasting accuracy over Direct SI and EDM in four of the five systems. However, the improvement depends non-monotonically on the number of cascade stages.
To explain this behavior, the authors introduce a theoretical framework describing the trade-off between the approximation error associated with learning long transitions and the loss of information caused by repeatedly conditioning on partially observed states. The analysis establishes conditions under which an intermediate cascade depth is optimal.
Critical strengths
1. Relevant research question and well-designed conditional evaluation benchmark.
The paper addresses an important problem in probabilistic forecasting: whether learning and composing shorter transitions can provide more accurate conditional distributions than directly learning the full forecasting horizon. I particularly appreciate that the work focuses on the quality of conditional distributions rather than simply generating plausible individual forecasts.
The construction of multiple reference trajectories sharing the same observed initial condition is a valuable contribution, as it provides a meaningful way to evaluate whether generative models recover the correct conditional distribution. The inclusion of several physical systems strengthens the experimental evaluation. I also appreciate the presentation of both the conditional mean and pointwise standard deviation in Figure 2, which provides valuable information about the quality of the learned distributions beyond individual generated samples.
2. Interesting theoretical interpretation of the cascading trade-off.
The distinction between approximation error and memory loss provides an interesting explanation for why increasing cascade depth does not necessarily lead to better performance. The theoretical results establishing conditions under which an intermediate cascade depth is optimal are particularly relevant.
Combined with the experimental improvements obtained by Cascaded SI across different physical systems, this provides a compelling motivation for investigating the trade-off between learning longer transitions directly and composing shorter transitions.
Critical weaknesses
1. General theoretical analysis is not sufficiently emphasized in the main paper (Section 4 and Appendix C).
While I appreciate the theoretical analysis, I find that some of the most interesting and general results are left in Appendix C. In particular, Section 4 mainly focuses on the rotation–OU model, while Appendix C develops a more general framework explaining why cascading can reduce approximation error and why repeated conditioning on partially observed states can introduce a memory error.
Theorem 11, for example, provides an interesting characterization of the limiting behavior of increasingly fine cascades under specific assumptions. I believe these results represent an important part of the scientific contribution and deserve greater emphasis in the main paper.
I would suggest including at least a concise presentation of the general theoretical results in Section 4, while keeping the detailed proofs in the appendix. This would help readers understand how the conclusions drawn from the stylized rotation–OU model relate to the broader class of dynamical systems considered in the paper.
2. Limited characterization of when cascading is preferable to direct forecasting.
In Section 3.3 and Figure 3, the authors study how forecasting performance changes with the cascade depth S, while keeping the final forecasting horizon T fixed for each physical system.
However, an important question remains: how does the relative performance of Direct SI and Cascaded SI change as the forecasting horizon itself increases? For relatively short horizons, directly approximating the conditional endpoint distribution might be sufficiently simple, while for longer horizons the advantage of composing shorter transitions could become more significant. On the other hand, repeated conditioning on incomplete observations could also lead to increasing memory loss.
Furthermore, the experiments do not directly isolate the contribution of memory loss to the performance degradation observed at larger cascade depths. Appendix C.6 introduces a theoretically motivated alternative that retains the initial observation throughout the cascade, but this variant is not evaluated experimentally.
These limitations make it difficult to establish precisely under which conditions cascading is preferable and to what extent the observed non-monotonic behavior is explained by the theoretical mechanisms identified in the paper.
Questions for authors
1. How does the optimal cascade depth change with the forecasting horizon T? (Section 3.3)
Would it be possible to extend the experimental evaluation by varying the forecasting horizon T and comparing Direct SI and Cascaded SI across different horizons and cascade depths?
In particular, a plot showing the forecasting error as a function of T for the different approaches, together with the evolution of the optimal cascade depth S*(T), would provide valuable insight into when cascading becomes advantageous and how its benefits change with the forecasting horizon.
I believe this would substantially improve our understanding of the applicability of the proposed method.
2. Can the effect of memory loss be isolated experimentally? (Sections 4.1–4.3 and Appendix C.6)
In lines 369–373, the authors explain that repeatedly conditioning on the current observed state can lead to information loss, even when the individual short-time conditional transitions are known exactly.
I find this distinction interesting, but I would appreciate a clearer discussion of how this mechanism relates to exposure bias and error accumulation in autoregressive forecasting.
In particular, exposure bias arises from the discrepancy between conditioning on ground-truth states during training and generated states during inference, while the memory error discussed here can occur even with exact transition kernels. Although these mechanisms are different, they may interact in practical learned forecasting systems.
Moreover, Appendix C.6 introduces an interesting alternative in which the initial observation X₀ is retained as additional conditioning information throughout the cascade. Proposition 12 shows that this construction recovers the correct endpoint conditional distribution when the transition kernels are exact.
Would it be possible to compare the proposed Cascaded SI with a variant that additionally conditions each transition on X₀? Such an ablation could help determine to what extent the observed degradation at large cascade depths is associated with memory loss, and whether retaining the initial condition provides practical benefits despite the additional conditioning complexity.
3. How sensitive are the conclusions to the distribution of hidden initial components? (Section 2)
The hierarchical sampling procedure is an interesting contribution, as it allows the authors to construct reference conditional ensembles by fixing the observed initial state and varying the hidden components.
However, I would be interested in understanding how sensitive the conclusions are to the distributions used to generate the hidden initial states.
Appendix B.1 describes the construction of these components for the different systems. In some cases, the observed and hidden Fourier components are generated independently.
Since the conditional forecasting problem is determined by the distribution of hidden states compatible with a given observation, could the authors discuss whether the results would change under different hidden-state distributions, particularly when observed and unobserved components are statistically dependent?
This would help establish how broadly the conclusions extend beyond the specific synthetic benchmark construction.
Additional minor presentation suggestions
-
Introduction, lines 30–32: I would suggest framing the problem more explicitly in terms of partially observed dynamical systems rather than primarily describing observations as coarse. Coarse-graining is one particular form of partial observation, while the broader problem also includes missing variables and incomplete measurements.
-
Section 2, line 79: The term "hierarchical sampling design" could be introduced more explicitly. Although the construction is subsequently described, a brief explanation of the two levels of sampling would improve readability.
-
Section 2, lines 95–100: When introducing the hidden initial components Z₀, I would suggest explicitly directing the reader to Appendix B.1, where their distributions and construction are described. A brief summary in the main text would also help clarify how the reference conditional ensembles are generated.
-
Section 3.1, lines 186–194: The statement that Direct SI should recover the correct conditional distribution in the ideal setting, whereas Cascaded SI need not do so under partial observation, is important and could benefit from a more intuitive explanation. In particular, briefly discussing the non-Markovian nature of the observed process would help readers understand the motivation for the subsequent theoretical analysis.
5 comments
2. Performance and optimal cascade depth across forecast horizons
“[…] how does the relative performance of Direct SI and Cascaded SI change as the forecasting horizon itself increases? For relatively short horizons, directly approximating the conditional endpoint distribution might be sufficiently simple, while for longer horizons the advantage of composing shorter transitions could become more significant. […] How does the optimal cascade depth change with the forecasting horizon ? (Section 3.3) Would it be possible to extend the experimental evaluation by varying the forecasting horizon and comparing Direct SI and Cascaded SI across different horizons and cascade depths? In particular, a plot showing the forecasting error as a function of for the different approaches, together with the evolution of the optimal cascade depth , would provide valuable insight into when cascading becomes advantageous and how its benefits change with the forecasting horizon.”
We have included the requested horizon–depth experiment and plot (Figure 6) in Appendix B.2.3. We studied five forecasting horizons on Euler, . We followed the benchmark protocol (same data, architecture, selection and metric) with three training seeds per configuration, and a fixed training-pair budget of 15,840 instead of 16,000 since 15,840 is divisible by every depth. At it reproduces the benchmark (; 16.6 vs. 16.3 for Cascaded SI).
Test csFID-10k (lower is better):
| Horizon | Direct SI | Cascaded SI | Selected |
|---|---|---|---|
| 0.2 | 41.3 | 19.2 | 4 |
| 0.4 | 66.6 | 20.0 | 8 |
| 0.6 | 72.3 | 17.9 | 8 |
| 0.8 | 65.6 | 18.1 | 8 |
| 1.0 | 59.8 | 16.6 | 10 |
Scores are averaged over three training seeds and ten test conditions. At each horizon, both methods are evaluated against the same horizon-specific reference ensembles.
Cascading improves performance at every horizon, by roughly a factor of two at and three to four at longer horizons. The selected depth generally increases with , from to . This is consistent with the preferred segment duration remaining between 0.05 and 0.1. The full depth sweeps in Figure 6 (Appendix B.2.3) also show that too deep cascading increases the error.
Absolute csFID values need not increase monotonically with , since each horizon has its own reference ensembles, so csFID-10k compares methods at a fixed , not one method across .
3. Memory loss versus error accumulation: the anchored cascade
“[…] the experiments do not directly isolate the contribution of memory loss to the performance degradation observed at larger cascade depths. Appendix C.6 introduces a theoretically motivated alternative that retains the initial observation throughout the cascade, but this variant is not evaluated experimentally. […] Can the effect of memory loss be isolated experimentally? (Sections 4.1–4.3 and Appendix C.6) […] Moreover, Appendix C.6 introduces an interesting alternative in which the initial observation is retained as additional conditioning information throughout the cascade. Proposition 12 shows that this construction recovers the correct endpoint conditional distribution when the transition kernels are exact. Would it be possible to compare the proposed Cascaded SI with a variant that additionally conditions each transition on ? Such an ablation could help determine to what extent the observed degradation at large cascade depths is associated with memory loss, and whether retaining the initial condition provides practical benefits despite the additional conditioning complexity.”
We ran this experiment, which Reviewer NnpT also requested, and extended the theory to learned anchored transitions.
With exact kernels, the anchored cascade recovers the correct distribution (Proposition 12). With a restricted function class, the approximation problem returns: each transition must now also represent its dependence on . This is the additional conditioning complexity that the reviewer mentions. In the rotation–OU model, this dependence is a rotation that oscillates faster as grows, and the quadratic anchored cascade keeps a positive error for every (Theorem 15). A neural-network test agrees: raw anchoring cuts the error at () but not at (), unless we rotate the anchor beforehand (0.0116).
The analysis implies a gain where the dependence on is simple and possibly none where it is complicated. And indeed:
- Passive scalar (affine conditional mean, Proposition 5): anchoring lowers the error at every depth (csFID-10k at , at ).
- Euler (nonlinear): anchoring does not help (16.32 against 17.39 at , 23.29 against 26.49 at ).
So retaining gives a practical benefit on passive scalar and none on Euler. In both systems, errors increase with depth under anchoring, so memory loss is not the sole cause of degradation. Errors in learned transitions can also contribute to the degradation and accumulate during rollout. Full results are in Appendix B.2.1 (Figure 5, Table 9) and Appendices C.8–C.9 (Theorem 15, Table 14).
4. Relation to exposure bias and error accumulation in autoregressive rollouts
“In lines 369–373, the authors explain that repeatedly conditioning on the current observed state can lead to information loss, even when the individual short-time conditional transitions are known exactly. I find this distinction interesting, but I would appreciate a clearer discussion of how this mechanism relates to exposure bias and error accumulation in autoregressive forecasting. In particular, exposure bias arises from the discrepancy between conditioning on ground-truth states during training and generated states during inference, while the memory error discussed here can occur even with exact transition kernels. Although these mechanisms are different, they may interact in practical learned forecasting systems.”
Super interesting question! A learned cascade has three separate sources of error:
- Memory error. The observed process is not Markov, so transitions that condition only on the current observed state lose information. This happens even with exact transition kernels (Appendix C.6).
- Transition error. Each learned kernel is imperfect, and these errors add up along the rollout.
- Exposure bias. A learned kernel is trained on true states and applied to generated ones, which can lie outside its training distribution.
The second and third vanish when the kernels are exact. The first does not. With exact kernels, the generated intermediate states even have the correct marginal distribution, so the model never leaves its training distribution, and the memory error is still there.
In learned cascades all three are present and can interact, as the reviewer says. The anchored experiment above shows this on passive scalar: conditioning on lowers the error at every depth, yet the error still increases with depth.
We thank the reviewer for their thoughtful and constructive feedback, particularly for highlighting the importance of our theoretical results. We have uploaded a revised manuscript alongside this response, incorporating additional requested experiments, theoretical analysis, and clarifications addressing the reviewer’s suggestions. Below, we respond to each point.
1. General theoretical results in the main paper
We thank the reviewer for this suggestion. We agree that the general theoretical results deserve greater emphasis in the main paper, and we have therefore expanded the introduction to Section 4 with two paragraphs summarizing the results on approximation error and memory loss developed in Appendix C.
The first paragraph explains how shorter transitions can reduce approximation error and how composing simple transition maps can capture dependencies that a single map cannot represent. The second explains why partial observation can make the observed process non-Markovian, so that even exact conditional transitions need not compose into the correct conditional endpoint distribution. We also provide a concise statement of Theorem 11, including its assumptions: for the deterministic dynamics considered there, increasingly fine cascades converge to a deterministic conditional forecast while preserving the correct one-time marginals, leaving a nonzero memory error whenever the true conditional forecast has nonzero spread.
These additions clarify the general mechanisms before the rotation–OU example, whose analysis remains unchanged. Detailed assumptions and proofs remain in Appendix C.