- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper proposes the Belief Flow Filter (BFF) for high‑dimensional physical‑system state estimation via Bayesian filtering. It propagates filtering belief through the weights of a persistent generative model and draws state samples from the updated generator. Experimental results demonstrate competitive reconstruction, spectral accuracy, and uncertainty calibration across physical systems with chaotic dynamics, sparse observations, and nonlinear observation models.
Critical strengths
- It is interesting to store the sequential filtering belief within generator weights. It offers an alternative route to recursive Bayesian filtering for high‑dimensional chaotic PDE systems, mitigating the curse‑of‑dimensionality suffered by particle‑based methods.
- The paper evaluates across multiple chaotic physical tasks covering 1D-PDE, 2D-PDE, low-dimensional ODE and a realistic-inspired tokamak simulation.
Critical weaknesses
- A primary motivation for BFF is reducing online cost by amortizing filtering updates in offline training. While the TTT weight‑update step is fast, inference runtime is still dominated by flow‑ODE‑based posterior sampling. A more systematic cross‑method computational comparison is desired, including training overhead, per‑observation update time, sampling latency and memory consumption. It should also be clarified whether reported timings adopt matched hardware, batch size, accuracy requirements and sampling budgets.
Questions for authors
-
The proposed method relies on a learned surrogate loss for online test-time updates. How does the surrogate loss approximate the ideal Bayesian filtering objective, and can the authors provide quantitative evidence that minimizing this surrogate leads to improved posterior estimates?
-
The theoretical analysis appears to apply to general recursive belief encoders, rather than specifically establishing the advantages of the proposed test-time training mechanism. What theoretical guarantees distinguish BFF from conventional recurrent belief encoders, such as GRUs?
-
The method requires test-time parameter updates and flow-based posterior sampling. Could the authors provide a comprehensive comparison of training cost, online update latency, posterior sampling time, and memory consumption against conventional Bayesian filtering methods and other learned filtering approaches?
-
The evaluation primarily uses metrics such as relative error and CRPS. How do the authors verify that BFF captures the joint posterior distribution, particularly in high-dimensional systems, rather than merely producing accurate point estimates or marginal distributions?
9 comments
Official Response to Reviewer 2RYr (2/3)
(Response to Comment 2, continued)
We first compare, across 20 trajectories, the time series of the surrogate loss and the ideal filtering loss, and observe significant correlation between them.
| Metric | Pooled Pearson | Pooled Spearman |
|---|---|---|
| Estimate | 0.6482 | 0.3707 |
| 95% confidence interval | [0.6021, 0.6893] | [0.3344, 0.4050] |
| Pairing-test P |
They have a pooled Pearson correlation of ~0.65, indicating moderate to strong correlation, and both correlations have a positive 95% CI. Both p-values reach the Monte Carlo resolution, showing that the surrogate loss and the ideal filtering loss have a statistically significant correlation in this experiment.
We then examine whether the learned negative gradient is a local descent direction for the ideal filtering loss. The gradient inner product is positive at 1,974 of 1,980 update contexts (99.70% of the steps, 95% CI: [99.29%, 100%]). Therefore, a sufficiently small gradient descent step on the learned surrogate loss would decrease the ideal filtering loss, which can be associated with the distributional posterior error using a Grönwall argument (Appendix F.4 in the revised manuscript). We have added these to Appendix J.11 in the revised manuscript. Please see that section for details of the experiment settings and results.
We also give a possible intuitive explanation to how the surrogate loss approximates the ideal Bayesian filtering objective. Given the update rule in Eq. (12), . Meanwhile, the ideal update is where is the ideal filtering loss.
Suppose we train the surrogate parameter to make the model's updated weight approach the oracle updated weight , the negative gradient of the learned surrogate loss would approach the displacement toward the oracle minimizer . Then, if the ideal loss is well-shaped (e.g., convex) and near so that its negative gradient is positively correlated with the displacement toward the minimizer, the gradients of the learned loss and the ideal loss can therefore be positively aligned.
We leave a more rigorous theoretical treatment for future work.
[1] Lin et al., On the Design of One-step Diffusion via Shortcutting Flow Paths, ICLR'26.
Comment3 (Q2): The theoretical analysis appears to apply to general recursive belief encoders, rather than specifically establishing the advantages of the proposed test-time training mechanism. What theoretical guarantees distinguish BFF from conventional recurrent belief encoders, such as GRUs?
We thank the reviewer for this comment. The theoretical result in Section 3.2 shows that our outer training loss controls the distributional error in Bayesian filtering. We agree that it also applies to conditional flow matching/diffusion filters that are conditioned on a latent state updated with recurrent models. We view a BFF-specific theoretical guarantee on convergence or a larger model capacity as an interesting future direction.
Meanwhile, we would like to clarify that theoretical results in the original manuscript consist of two major parts. In addition to the results mentioned above (Section 3.2 in the revised manuscript), we also derived the weight space update rule for Bayesian filtering (Section 2.3 and 3.1 in the revised manuscript). This theoretical result guides us to design the weight-space gradient update and the specific form of the surrogate loss in our BFF method, instead of using a generic recurrent belief encoder.
We also provide empirical evidence in our new experiments to show that this design is better than GRU or a generic gradient update. Please see our results in Appendix J.2 and J.10 in the revised manuscript, or our response to Reviewer STer comment 1 and VhJ9 comment 2.
Official Response to Reviewer 2RYr (3/3)
Comment4 (Q4): The evaluation primarily uses metrics such as relative error and CRPS. How do the authors verify that BFF captures the joint posterior distribution, particularly in high-dimensional systems, rather than merely producing accurate point estimates or marginal distributions?
We thank the reviewer for this insightful question. We agree that evaluating the distributional accuracy of the joint posterior distribution is important.
We clarify that the metrics in the original manuscript span sample-wise accuracy (field relative L2 and spectrum deviation) and distributional calibration and sharpness (MA and CRPS). A point estimate would fail on distributional metrics, while a distribution marginalized over history-information conditions would be bad on sample-wise accuracy. However, these metrics are indeed less sensitive to spatial dependence of the posterior.
Therefore, to further test whether BFF learns the joint posterior or a spatially independent marginal distribution, we designed a spatial-dependence diagnostic on the NS uniform and NS moving-sensor (both are dimensional) benchmarks.
We use the p=1 variogram score (VS), which measures how well the model posterior predicts actual samples' spatial differences, and thus reflects spatial dependence on the posterior distribution:
where and are actual field values at locations and , and and are the field values of the -th sample in the model posterior ensemble conditioned on the same history observations.
To test that BFF captures the joint spatial distribution, we compare the VS of the spatially independent marginal distribution with that of the original joint posterior. We approximate the model's spatially independent marginal (i.e., product of pointwise marginal distributions) by randomly shuffling the sample index for each selected location. If the original joint posterior distribution has a VS lower than that of the marginal distribution, then we have evidence that BFF learns a meaningful joint spatial distribution.
We summarize the results in the table below (4 displayed decimals). Please see Appendix J.6.1 for more detailed configuration of the evaluation.
| NS moving sensor | NS moving sensor | NS moving sensor | NS moving sensor | NS uniform | NS uniform | NS uniform | NS uniform | |
|---|---|---|---|---|---|---|---|---|
| Spatial distance | Original VS ↓ | Shuffled VS ↓ | Rel. change after shuffle | 95% CI for relative change | Original VS ↓ | Shuffled VS ↓ | Rel. change after shuffle | 95% CI for relative change |
| 1 pixel | 0.0142 | 0.1899 | 1233.99% | [816.46%, 1761.40%] | 0.0131 | 0.0515 | +294.73% | [160.98%, 439.62%] |
| 4 pixels | 0.0880 | 0.1624 | 84.52% | [53.40%, 123.36%] | 0.0467 | 0.0571 | +22.17% | [11.98%, 30.03%] |
| 16 pixels | 0.4002 | 0.4063 | 1.53% | [0.006%, 3.19%] | 0.1437 | 0.1436 | −0.06% | [−1.50%, 1.10%] |
| 32 pixels | 0.5539 | 0.5547 | 0.14% | [−0.68%, 0.86%] | 0.1568 | 0.1567 | −0.10% | [−0.73%, 0.27%] |
We observe that for the moving sensor or uniform sensor NS scenarios, the spatial joint posterior has a lower VS than the marginal one at spatial distances pixels for moving sensors and pixels for uniform sensors. We note that for uniform sensors, the sensor is placed with a spacing of roughly pixels, so the spatial correlation of the posterior uncertainty conditioned on the sensor observation would decay in this interval. In contrast, there is only one sensor in the moving sensor setting, which allows larger spatial regions for uncertainty.
Additionally, we compared the VS of BFF with the posterior modeling baselines in the NS uniform setting, averaged over the four pair distances (1, 4, 16, 32).
| Method | Original VS ↓ | Shuffled VS ↓ | Relative change after shuffle |
|---|---|---|---|
| BFF | 0.09009 | 0.10224 | +13.49% |
| SDA | 0.05332 | 0.0560 | +5.04% |
| FlowDAS | 1.5769 | 2.7891 | +76.87% |
| EnSF | 0.5809 | 0.5827 | +0.31% |
| EnKF | 0.4304 | 0.4304 | −0.00% |
Compared to the baselines, the original VS of BFF is the second best. We note that SDA is underconfident, with a high miscalibration area ~0.43 on NS (see Table 1 in the manuscript), and it makes predictions with less spatially correlated fluctuations. This is reflected in its smaller relative VS change after shuffling. Meanwhile, FlowDAS has a worse VS absolute value. EnSF and EnKF demonstrate little relative VS increase after shuffling, suggesting their posteriors are not much more informative than the corresponding spatially independent marginals.
These results indicate that BFF's posterior captures a reasonable spatially joint distribution. We have added these results in Appendix J.6.1 in the revised manuscript.
Official Response to Reviewer 2RYr (1/3)
We thank the reviewer for the detailed and constructive review comments. We are encouraged that the reviewer recognizes that our method is interesting, is a promising alternative to conventional particle-based filters, and is evaluated in different physical tasks. Next, we address the concerns of the reviewer one by one:
We thank the reviewer for this comment. We conducted a new benchmark of all methods reported in Table 1 NS and KS. Below, we summarize the benchmark results on the NS experiment:
The time is measured on a single H800 GPU. We did not force the methods to match accuracy or sampling budget requirements. Instead, we use configurations that produce Table 1 results so that the benchmark corresponds to the actual experiments. The inference batch size is 1 except for EnKF and EnSF because they need ensemble updates inherently. For SDA and FlowDAS, their update and sampling steps are coupled, so we only report a combined time.
These results demonstrate that the update of BFF is fast, comparable to deterministic methods like FNO or Transformer. BFF's inference time can be dominated by the ODE integration. Therefore, it can be accelerated if its performance does not drop too much when the sampling steps decrease. We show that this is possible in NS (Table 4 in the revised manuscript) and the Tokamak experiment (Table 6 in the revised manuscript).
We have added the complete benchmark results and detailed configurations into Appendix J.1 in the revised manuscript.
We thank the reviewer for this question. We agree that directly assessing the correlation between the surrogate loss and the ideal Bayesian filtering loss would strengthen the validity of our method design.
First, we clarify that we did not make rigorous theoretical claims in the manuscript that the learned surrogate loss converges to the ideal Bayesian filtering loss. However, we did observe evidence suggesting that our learned loss is positively correlated with the Bayesian ideal filtering loss, and the directions of their gradients are aligned in the high-dimensional weight space.
Because the ideal loss in Eq. (9) is intractable in high-dimensional space as discussed in Section 2.3, we did additional diagnostic experiments on the 3-dimensional Lorenz 63 system. There, we can approximate the ideal filtering loss by sampling from the model posterior, propagating, reweighting with the likelihood, and then approximating the ideal marginal velocity field uKbθt using Monte-Carlo estimation (please see Eq. 77, Appendix J.11 of the revised manuscript, and also, e.g., Eq. 12 in [1]).
With this approximated uKbθt, we can approximate the ideal loss ℓ⋆ (Appendix J.11 Eq. 79), and do diagnostics. Please see the details in Appendix J.11.1 in the revised manuscript.