- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces SLiSDE, a Neural SDE architecture that uses structured linear stochastic layers to reduce simulation costs. Each discretized layer forms an affine recurrence compatible with parallel associative scan, while gated in-flow stacking preserves nonlinear expressivity by allowing preceding-layer paths to modulate the next layer’s transition and offset. For functional calibration, the authors introduce an optional Girsanov tilt that increases the frequency of rare paths under an auxiliary sampling distribution. An exact likelihood-ratio correction enables estimation of expectations under the original model, with the aim of reducing Monte Carlo error and improving tail-sensitive calibration. The paper presents theoretical results on well-posedness, discretization error, validity of the change of measure, and terminal-law universality, together with experiments on a synthetic path-functional benchmark and the DAX and SPX option-surface benchmarks.
Critical strengths
- Scan-compatible structured dynamics. The structured linear SDE layers yield affine recurrences compatible with associative scan, enabling parallel-in-time simulation without introducing an additional approximation to the discretized recurrence.
- Expressive nonlinear coupling. Gated in-flow stacking introduces nonlinearity through inter-layer coupling while preserving affine dependence within each layer. This enhances expressivity without sacrificing scan compatibility.
- Targeted rare-path sampling. The Girsanov tilt addresses the difficulty of sampling rare paths in functional calibration by learning a proposal that visits relevant tail regions more frequently. Likelihood-ratio correction allows these samples to estimate expectations under the original model, offering a way to improve tail-sensitive estimation.
Critical weaknesses
- The architectural contribution needs clearer differentiation from prior work in selective state-space models. The principle of input-dependent gates modulating linear recurrences is present in structured sequence models such as the structured linear CDE SLiCE (Walker et al., 2025). While SLiSDE successfully adapts this to Brownian-driven SDE layers, the paper would benefit from explicitly stating what uniquely emerges from the stochastic setting that a deterministic gated recurrence could not achieve. For instance, does the independent Brownian driver per layer enable qualitatively different dynamics than a deterministic gated CDE? A brief discussion would clarify the novelty.
- The gating mechanism is not isolated by ablation. All reported SLiSDE variants use gated in-flow (Appendix C), and Table 5 ablates only noise type and block size. The contribution of the gate itself, inter-layer nonlinearity via path-dependent modulation, is not directly compared against alternatives such as: (a) a simple concatenation-based coupling without learned gates, (b) untrained (random or fixed) gates to isolate the effect of learning, or (c) a single deep structured layer with matching parameter count to isolate the effect of depth. Without such comparisons, the reported improvements cannot be attributed specifically to the gating design.
- The main-text presentation should better reflect the qualified empirical results. The Girsanov tilt is presented as a contribution, but its quantitative comparisons and controller ablations appear only in Appendix E, with a brief summary in Sect. 6.2. It may be better to list the results of Girsanov tilt in main text.
- Please check the reference section carefully. The citation 'H. Smith et al. Calibrating generative models to distributional constraints' is not completed and remains revision marks.
- The paper uses for both model parameters and Girsanov controller parameters . While clearly differentiated in Appendix C.8, the main text could be clearer.
- Table 1 title shows "Computational cost of composing affine transition maps", but the Neural SDE column reports recurrent cost, not scan cost.
Questions for authors
Please refer to 'Weaknesses'.
2 comments
Response to Reviewer USAb (2/2)
Weakness 2: Gate ablation
We ran the three ablations the reviewer proposes, and two more that separate the two gates. All follow the paper's protocol on the SLiSDE cells of Tables 2–4 (two and three layers on each dataset), with seven seeds, and each variant is compared with the full model seed by seed.
- (a) Coupling without a learned gate: the previous layer's state enters the next layer through a plain linear map.
- (b) Untrained gates: both gates are kept, frozen at their random initialisation.
- (c) A single layer: one structured layer at widths 32 to 256, the widest with more parameters than the two-layer stack.
- Each gate alone: the flow gate without the offset gate, and the reverse.
The table gives the loss relative to the full model (geometric mean over seeds; above 1 means the full model is better; p from a paired t-test on the log-ratios).
| Cell | (a) Linear coupling | (b) Frozen gates | Flow gate only | Offset gate only |
|---|---|---|---|---|
| TOY, 2 layers | 1.38 (p = 0.09) | 6.90 (p < 0.001) | 0.93 (p = 0.60) | 0.84 (p = 0.43) |
| TOY, 3 layers | 0.98 (p = 0.94) | 7.91 (p < 0.001) | 0.97 (p = 0.88) | 1.26 (p = 0.14) |
| DAX, 2 layers | 1.79 (p = 0.002) | 1.09 (p = 0.61) | 0.87 (p = 0.06) | 1.22 (p = 0.12) |
| DAX, 3 layers | 3.47 (p = 0.001) | 2.21 (p = 0.007) | 1.54 (p = 0.01) | 1.50 (p = 0.003) |
| SPX, 2 layers | 1.42 (p = 0.05) | 2.08 (p < 0.001) | 1.44 (p = 0.001) | 1.19 (p = 0.26) |
| SPX, 3 layers | 1.63 (p = 0.02) | 1.85 (p < 0.001) | 1.06 (p = 0.35) | 1.01 (p = 0.94) |
Learning the gates matters in five of the six cells (column a and b). In short, the gated stack earns its place on the two real option surfaces, while on the synthetic benchmark a single structured layer is already enough.
For ablation (c), the same ratio for the best single layer, relative to the better of the two- and three-layer full models:
| (c) | TOY (2 layers) | DAX (3 layers) | SPX (2 layers) |
|---|---|---|---|
| Best single layer | 1.01 (p = 0.98) | 1.49 (p = 0.003) | 1.95 (p < 0.001) |
Weaknesses 3–6
We appreciate these suggestions and have followed them. The Smith et al. citation is completed, the controller parameters are now throughout, with reserved for the backbone, and Table 1 separates the sequential work, the parallel time and the total work of the scan. The principal results of the Girsanov tilt are stated in Section 6, and we intend to move the DAX calibration results (Table 9) there in the final version together with a more detailed explaiation of the experiments and performance.
As for Table 1, the Neural SDE (parallel) scan cost is not reported because Neural SDEs do not admit a parallel scan (no associative flows). We have clarified this in the manuscript.
Response to Reviewer USAb (1/2)
We thank the reviewer for the careful reading. The current version of the work addresses all the remarks.
Weakness 1: Differentiation from selective state-space models
Input-dependent gates modulating linear recurrences are central to selective state-space models, including SLiCE (Walker et al., 2025). We have clarified this connection in Section 3.3 and made the distinction from our architecture more explicit.
The main difference is not simply that SLiSDE is stochastic: our SLiCE baseline is also driven by Brownian motion and therefore produces random paths. Rather, the distinction concerns how stochasticity enters the architecture and how it interacts with the gated layers.
In the SLiCE baseline, each successive block processes the path produced by the preceding block, without introducing an additional stochastic driver. In SLiSDE, each layer is instead a linear SDE with its own diffusion coefficients and Brownian driver. The previous-layer path modulates the coefficients through causal gates, but does not itself serve as the driving signal. This provides two additional capabilities:
Independent drivers. The reviewer asks whether independent drivers produce qualitatively different dynamics. In law they do, as the first point shows; in calibration they make no statistically significant difference (improvement) for the experiments we have considered. The original experiments use a shared Brownian motion on TOY and SPX and, on DAX, drivers correlated with the first through a learned coefficient initialised at 0.95 (now documented in Appendix D). We retrained the two- and three-layer configurations of Tables 2–4 with an independent Brownian motion in each layer, all other settings unchanged, with seven paired seeds. The table reports the loss ratio between the independent-driver and original configurations (geometric mean; p from a paired t-test on the log-ratios).
No configuration shows a statistically significant difference. A layer can therefore be given a driver of its own at no measurable cost, which is precisely what the last-layer Girsanov tilt requires.