- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper presents Coupled Bidirectional Survival Transport (CoBiST), a generator-agnostic cross-horizon transport operator designed for probabilistic time-series forecasting. Given an observed sequence history and a forecast horizon , the authors define a conditional generative forecasters to estimate the joint future distribution by mapping noise to generated paths . the method CoBiST replaces standard sequence backbones with a unified transport core operating on sequence states .
Critical strengths
The methodology relies on rigourous Transport theory, the method CoBiST couples bidirectional scans, memory decay, and direct local routing into a unified, row-stochastic route simplex. The paper provides complete theoretical proofs: Theorem 1 uniquely characterizes the geometric-mean coupling budget from axiomatic hazard principles; Theorem 2 & Proposition 2 derive an exact row-stochastic augmented kernel with explicit source attributions; Theorem 3 proves rank-one semiseparability achieving exact time/memory complexity; and Theorem 4 guarantees frozen-gate non-expansiveness.
On the experimental side, I noted the The transport core is modular and easily inserted into GAN, Flow-matching, and Diffusion interfaces without altering outer training losses or samplers (Table 1). Across eight diverse benchmarks.
Critical weaknesses
I will appreciate to see a more formal explanantion distinction between Frozen-Gate Non-Expansiveness and State-Dependent Multi-Step Dynamics, I noted in Theorem 4 they established that the frozen-gate transport core is non-expansive (), Proposition 4 (Appendix B.1) reveals that state-dependent gates introduce finite correction terms scaling with horizon length (). While the authors explicitly document this qualification, the manuscript lacks an empirical quantification of how gate Lipschitzness affects perturbation growth across multi-step reverse ODE/SDE sampling trajectories in Flow and Diffusion models.
Questions for authors
Reflecting on what I have mentioned in the Critical Weaknesses, I want to emphasis on Proposition 4, the state-dependent bound contains a term that grows linearly with forecast horizon . In practice, do you use explicit gate regularization (e.g., spectral normalization, logit bounding, or weight decay on ) to control for longer horizons such as Wind ()?
Also, in the ablation studies (Table 5 and Section 5), the Neural- ablation performs comparably to the axiomatic geometric mean . Did you observe any specific dataset regimes or horizon lengths where Neural- learned non-geometric coupling budgets that significantly improved or degraded performance?
4 comments
Response to Reviewer Wu3t Part 2/2
Q2: Neural- across datasets and horizons
It's worth noting that we follow the suggestions by other reviewers and revise the Nerual- experiments to a more convinced design. In the revision, the new revised Neural- now estimates directly by a network taken local and context embeddings as input. It is independently tuned fairly under the same protocol (Appendix D.3).
Table 3 gives the following PCRPS improvement rates (%), mean (std), across all eight datasets of CoBiST over the revised Neural-:
| Model comparison | Elec. | Exch. | Traffic | M4 | Wiki | Taxi | Wind | Weather | Mean gain | [95% CI] |
|---|---|---|---|---|---|---|---|---|---|---|
| CoBiST-GAN vs Neural- | 1.03 (7.36) | 12.30 (18.98) | -1.99 (2.31) | 8.33 (6.71) | 0.92 (8.64) | -0.46 (3.50) | 2.44 (28.74) | -9.75 (4.57) | 1.60 | [-3.79, 7.24] |
| CoBiST-Flow vs Neural- | -0.05 (0.47) | 4.40 (3.99) | -0.71 (0.73) | -0.20 (0.59) | 0.43 (0.34) | 0.18 (0.63) | 3.94 (1.93) | -0.11 (1.79) | 0.98 | [-0.19, 2.46] |
| CoBiST-Diffusion vs Neural- | 0.03 (0.26) | -0.63 (1.68) | 0.05 (0.20) | -0.45 (1.24) | -0.21 (0.47) | 0.05 (0.12) | -0.89 (1.42) | -1.49 (4.41) | -0.44 | [-1.19, 0.09] |
Generally, Neural- is close to CoBiST without significant difference, supporting the geometric mean as a simple, semantically interpretable choice with competitive accuracy. Detailed results of other scores and raw metrics are reported in Appendix E.1. Most differences between Neural- and CoBiST are not significant. We therefore can hardly statistically established regimes for possible significant improved or degraded performance.
I thank the authors for their extensive response, I appreciate the derivation about the new condition erivations under Lipschitz asumptions and the new empirical perturbation, this allow to effectively quantify how gat feedback behave across multu-step trajectories. This resolves my concerns regarding state-dependant dynamics. The revised q-ablation (using q ) was a a rigorous update whcih I needed to see to validate your architectural design choice.
Based on the rebruttal updates, I am increasing my score.
Thank you for recognizing our effort!
Thank you for recognizing our effort and your valuable comments. Your suggestions help us develop the newer and more appliable dynamic gate theory. Related sensitivity experiments provide further empirical support on it. Your comment regarding the geometric mean and regularization is also insightful. We would appreciate it if you could increase your rating as you mentioned, which is extremely important for us.
Response to Reviewer Wu3t Part 1/2
We thank the reviewer for pointing out the gap between frozen-gate stability and state-dependent gates in iterative sampling.
W1 / Q1: State-dependent transport and multi-step dynamics.
Dynamic-gate theory under Lipschitz assumptions
We previously derive the frozen-gate theory because we didn't add assumption on the gate. We realized that the frozen-gate theory is less applicable, so we have replaced all related theory with a stronger conditional result under Lipschitz assumptions. Under Assumptions 1–2, for a fixed context and common boundaries, let embedded states have norm at most B, retention logits have Lipschitz constant Lb, and the difference of direction logits have Lipschitz constant Lℓ. For δ=maxj∥zj−zj′∥2, with gates recomputed for each input, Theorem 4 states
\le (1+2BL_b)\delta,$$ $$\max_k\{\|T _ k-T' _ k\| _ 2,\|D _ k-D' _ k\| _ 2\} \le \left(1+2BL _ b+\tfrac{B}{2}L _ \ell \right) \delta.$$ For realized gates, **Proposition 3** retains the kernel-level statement $$\|K _ {\mathrm{real}}\| _ \infty\le1, \qquad \rho(K _ {\mathrm{real}})\le1.$$ This supports the frozen-gate qualification with common boundaries. **Proposition 4** makes the additional state-dependent terms explicit: $$D_ZT[\dot Z] =K(\mathcal G(Z,c))\dot Z +(D _ ZK[\dot Z])Z +(D _ ZK_\partial[\dot Z])\xi.$$ The first term applies the realized kernel to the perturbation while the other two describe gate feedback. Theorem 4 bounds their combined effect. Appendix B.1 also gives a conditional complete-generator bound. If the embedding and positionwise readout have constants $L_E$ and $L_R$, and $L_{\mathrm{tr}}=1+2BL_b+(B/2)L_\ell$, then $$\|v(U)-v(U')\| _ {\infty,2} \le L _ RL _ E\sqrt{1+(2+4B^2)L _ {\mathrm{tr}}^2} \|U-U'\| _ {\infty,2}.$$ For a discrete sampler $U_{n+1}=a_nU_n+b_nv_n(U_n)+s_n\eta_n$ with state-independent scalar coefficients, matched additive noise, and full-field constants $L_{v,n}$ on the relevant domains, it also derives $$\|U _ N-U _ N'\|_{\infty,2} \le\prod _ {n=0}^{N-1}(|a _ n|+|b _ n|L _ {v,n}) \|U _ 0-U _ 0'\| _ {\infty,2}.$$ **Empirical perturbation growth and gate feedback** We add a new experiment to test whether CoBiST attenuates perturbations when its gates adapt to the perturbed input, within a single transport operation and through complete sampling. We first perturb the embedded horizon representation by $10^{-5}$ to $10^{-1}$ of its norm and recompute all gates. All dataset-wise median transport response ratios remain below $0.9$ and vary little with perturbation size (Figure 3 (a)--(c)). Next, we perturb the initial Flow or Diffusion sampling state by $1\%$ and track the distance between paired runs, reported in Figure 3 (d),(e). Generally, these results **support CoBiST's ability to combine adaptive cross-horizon routing with attenuation of the tested perturbations** across all three generator families, and most evaluated Flow and Diffusion samplers also attenuate initial-state perturbations over complete sampling (except amplification for Weather). We also examine the contribution of gate feedback through reference-gate replay controls in Appendix E.4. **Regularization at longer horizons** Our current CoBiST models do not use explicit regularization designed to control the gates or their sensitivity along the forecast horizon. In preliminary tests, we observed that some regularization strategies could be helpful, but their performance are sensitive to datasets. Therefore, currently we havn't identified a good regularizer to characterize the trade-off between forecasting accuracy and stability. We have written the horizon-wise regularization as a limitation of the current work into the manuscript and leave this for future work.