- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2(+1)
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper investigates the potential incompatibility between conditional-mean prediction under squared loss and exact pointwise composition. Under coverage and Lipschitz assumptions, it relates composition defects to excess prediction risk, studies sharpness and conditions for mean composition, and constructs Chapman–Kolmogorov-consistent kernels using affine Gaussian latent dynamics.
Critical strengths
- Propositions 1 and 5 establish sharp smoothness dependence and matching small-noise risk orders in specific examples, strengthening the analysis beyond a qualitative observation about non-composing means.
Critical weaknesses
-
The paper provides a careful characterization of the incompatibility between conditional-mean prediction and exact composition. However, its practical implications beyond this characterization remain less established. In particular, the restricted kernel family in Section 4 illustrates a compatible distributional construction, but the evidence for choosing this particular construction for point forecasting is limited.
-
The quantitative applicability of the risk bound remains unclear beyond the controlled examples. Although the paper discusses the coverage and regularity assumptions and evaluates the constants in the oracle setting, it provides limited guidance on when these conditions yield an informative bound for realistic learned predictors.
Questions for authors
-
How do the risk bound and sharpness results extend the recursive-forecasting bias analyses? What is the main additional theoretical insight?
-
For point forecasting, what advantages or trade-offs does the kernel construction in Section 4 offer relative to the mean-preserving target
3 comments
Thank you for your thorough and thoughtful rebuttal. I appreciate the effort you have put into addressing my questions and concerns. I was impressed by the breadth and diversity of the experimental evaluations, as well as the detailed clarifications provided in your response. Your rebuttal has addressed most of my concerns, and I will therefore raise my score by one point.
Thank you again for your dedication and the substantial effort invested in this work.
Thank you for the updated assessment
Thank you for taking the time to read our response and for raising your score. Your positive feedback means a lot to us.
Your review helped us improve the paper in several ways. We are also glad the breadth of the experiments came through: it reflects the generality of the result, which applies to any predictor built to compose.
Thank you once more for your time and for providing a constructive review.
Beyond recursive bias, and when the bound is informative
Thank you for reviewing our work, for your thoughtful questions, and for highlighting Propositions 1 and 5. Below, we address each of your points.
1. The main additional insight (Q1). Recursive-bias analyses show that iterating a given one-step model yields a biased multi-step forecast. Our result is that this bias cannot be trained away while the predictor still composes: it belongs to the target, not to the estimator. When the true means do not compose, every predictor built to compose (rollouts, flow maps, consistency-trained models, conjugate architectures) must carry the defect somewhere: on the data, in its sensitivity, or at intermediate means that training never visits (Theorem 1, eq. 5). Propositions 1 and 5, which you highlighted, show that the trade-off is exact in its rates: L2R∗(L)→27/64 in smoothness and Θ(ϵ2) in noise. Training a composing network through its rollout illustrates it: the lag-1.6 excess falls from 60.4 to 53.7 while the lag-0.05 excess rises 75–173-fold, and the direct network's 8.14 stays out of reach (App. L, p. 38).
Three further results make this usable:
2. When the bound is informative (W2). Two conditions: the target defect exceeds the one-step error, and the data cover the intermediate means. The second can be checked in simulation through the effective coverage ratio, the error at the intermediate means divided by the error on data (Section 2, p. 4).
3. The kernel and the mean-preserving target for point forecasting (Q2, W1). You are correct that the evidence does not single out the closed form of Section 4 for point forecasting, and Section 4 now says that forecasting does not require it (p. 7). Where the dynamics have this form, its advantage is an exact likelihood at every lag, including unseen ones: on warped OU, excess error 0.001 at the held-out lag 1.5, against 0.148 for a direct network (Table 2, p. 25). Its limit is scope: with additive noise, only affine drifts admit it (Propositions 6 and 8). The two practical options meet different needs. On Lorenz-96 at lag 1.6, with the point rollout and direct heads as references:
The target needs observed intermediate states and one head per lag; the kernel needs a single one-step model with a noise model, and its value removes Monte Carlo noise (1.07 without this correction). The target therefore suits point forecasts at fixed horizons, while the kernel adds accuracy and uncertainty estimates at a much higher inference cost. A fitted kernel can also improve existing models without retraining, by 25–40% for U-Net and FNO on a measured cylinder wake (Figure 5, p. 9), though tuned rollout filters match or outperform it on FSI, for CNO, and in most of the broader benchmark (Apps. S.1–S.2). Figure 28 (p. 73) summarizes these trade-offs.
We hope these responses address your concerns and welcome any further discussion on these points.