- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the convergence behavior of Online Training Through Time (OTTT) for spiking neural networks, focusing on its fixed-parameter accumulation variant (OTTTA). The authors introduce a smoothed spiking model as an analytical reference and decompose the bias of OTTTA into two components: the hard–soft mismatch between discrete and smoothed spike trajectories, and the temporal-decoupling error between soft OTTT and full soft-BPTT. Under several regularity and stability assumptions, they derive a non-asymptotic bound on the hard-spike risk that explicitly accounts for these two sources of approximation error. The paper also proposes diagnostics for measuring these discrepancies and evaluates their behavior on CIFAR-10, CIFAR-100, CIFAR10-DVS, and DVS Gesture. The experiments examine discrepancy magnitudes, their evolution during training, their correlations with classification accuracy, and the effect of the smoothing scale.
Critical strengths
The paper separates hard–soft mismatch from temporal-decoupling error and incorporates both into a finite-step risk bound. This provides a useful framework for understanding different sources of gradient approximation error in OTTTA.
And the authors examine how the two discrepancies evolve during training and vary across datasets. The multi-seed experiments and additional sensitivity analyses provide some interesting observations about the relationship between gradient approximation errors and model performance.
Critical weaknesses
The main theorem relies on several strong assumptions, particularly the restricted PL condition and hard–soft trajectory stability. However, the paper does not discuss whether these assumptions hold, even approximately, for the networks used in the experiments. The resulting bound also contains residual terms related to the threshold-tail functional and temporal-decoupling discrepancy, but it is unclear whether these terms are sufficiently small to make the bound informative in practice. In addition, the finite-horizon stability factor in Appendix A.3 may grow rapidly with the number of time steps. I would like to see a more concrete analysis of these quantities and a clearer explanation of what the result tells us beyond existing convergence analyses of biased SGD.
And I find the experimental evaluation somewhat limited. While the paper analyzes the two approximation errors and their relationships with model accuracy, it does not directly examine whether reducing these errors leads to better training outcomes. More systematic ablations would be helpful, particularly regarding the number of time steps, smoothing scale, and network architectures. In addition, the experiments are restricted to four relatively small vision benchmarks. Since the proposed framework is intended to characterize online SNN training more generally, I would like to see evaluations on other modalities, such as auditory datasets like SHD and SSC, as well as larger-scale benchmarks such as ImageNet. Without broader experiments, it is difficult to assess how well the theoretical findings and proposed diagnostics generalize across different tasks and network configurations.
Questions for authors
-
Can the authors provide evidence that the convergence bound is informative for the networks used in the experiments? In particular, it would be helpful to examine the magnitude of the residual terms and discuss whether the restricted-PL and trajectory-stability assumptions are reasonable in these settings.
-
Do the proposed diagnostics provide actionable information about training? For example, if the dominant approximation error is reduced, does this consistently improve optimization or test accuracy?
-
How does the relative importance of hard–soft mismatch and temporal decoupling change with the simulation horizon? Since the analysis focuses on temporal approximation errors, experiments varying the number of time steps within the same dataset would be particularly informative.
4 comments
Author Response (2/2): Simulation Horizon and Reproducibility
Critical Weaknesses 1–2 · Question 3 · Within-dataset horizon and stability
The dominant discrepancy changes within CIFAR10-DVS with fixed event coverage and fixed weights. We rebinned each of the same 64 complete test recordings into 5, 10, or 20 frames in acquisition order using equal-event-count bins, with the remainder in the last bin. All settings use the same five final checkpoints trained at , the same membrane time constant (), and the loss averaged over the observed steps. The rebuilt 10-frame inputs match the original inputs exactly, and the diagnostics reproduce the earlier results for all five checkpoints. Within each spike mode, OTTT and BPTT produced identical stepwise logits at all three settings.
| Frames, full event window | OTTT hard–soft gap | Hard temporal gap | Soft temporal gap | Hard temporal / hard–soft | Soft temporal / hard–soft | Seeds with ratio above one, hard / soft |
|---|---|---|---|---|---|---|
| 5 | 704.22 | 644.22 | 495.33 | 0.915 | 0.703 | 1/5 / 0/5 |
| 10 | 323.71 | 402.91 | 374.02 | 1.245 | 1.155 | 5/5 / 5/5 |
| 20 | 497.06 | 517.09 | 515.96 | 1.040 | 1.038 | 3/5 / 3/5 |
We average per-example squared gradient differences within each seed and divide the across-seed means. The counts use each seed’s own ratio. From 5 to 10 frames, both temporal gaps decreased in absolute terms. The hard–soft gap fell by a larger fraction, so both ratios rose in all five seeds. The hard ratio crossed one in four seeds and the soft ratio in all five. At 20 frames, both aggregate ratios returned close to one. Meanwhile, from 10 to 20 frames, mean OTTT–BPTT cosine fell from 0.9194 to 0.9002 on the hard trajectory and from 0.9292 to 0.9080 on the soft trajectory. The ratios track the relative sizes of the two discrepancies, and cosine tracks the alignment of the update directions.
The rebinning intervention jointly changes events per frame and the number of membrane updates per recording. The fixed-input intervention tests memory directly. Increasing the membrane time constant from 2 to 4 at ten frames raised the hard and soft temporal gaps to 1306.13 and 1425.97.
In Appendix A.3, the revised sufficient-condition argument will carry the previous membrane difference through Eq. (1). For the default sigmoid scale, unit threshold, and leak of 0.5, the temporal coefficient after separating the pointwise spike mismatch is bounded by 0.5 in each layer. Geometric summation gives a sufficient forward stability factor uniform in the horizon with shared initialization, fixed depth, and uniformly bounded effective layer operators. The size of that factor and the remaining Eq. (13) constants depend on the configuration.
Critical Weakness 2 · Reproducibility and scope
The benchmark-level discrepancy ordering holds across ten consecutive seeds (2022–2031) per vision dataset, using the original settings and 128 diagnostic examples per run at epoch 299. The soft temporal gap exceeds the OTTT hard–soft gap in 0/10 CIFAR-10 runs, 0/10 CIFAR-100 runs, 9/10 CIFAR10-DVS runs, and 10/10 DVS Gesture runs. The corresponding ratios of mean gaps are 0.276, 0.263, 1.220, and 4.270.
In the exploratory accuracy analysis, we pool the original five runs with five outcome-selected runs per dataset. The pooled Pearson coefficients have the same signs and similar magnitudes as those of the original five runs.
We also evaluated a feedforward LIF MLP on the auditory SHD benchmark at using the same ten seed IDs. On 128 test examples per final checkpoint, the mean OTTT hard–soft and soft temporal gaps were 42.58 and 72.84, respectively. The ratio of these means was 1.711, and the soft temporal gap was larger in all ten runs. The SHD experiment extends the diagnostic comparison to an auditory dataset and a different architecture.
References
- Ahmad Ajalloeian and Sebastian U. Stich. 2020. On the Convergence of SGD with Biased Gradients. arXiv:2008.00051. Full text
- Hamed Karimi, Julie Nutini, and Mark Schmidt. 2016. Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition. ECML PKDD, 795–811. Full text
Follow-up
Thank you again for asking whether the diagnostics can guide training and how the discrepancy ordering changes with the simulation horizon. As the discussion period draws to a close, we would appreciate your feedback on the paired two-step correction experiment in Q2 and the fixed-event-coverage comparison in Q3. Is there a specific point in either comparison that would benefit from further clarification?
Dear Reviewer,
This is a kind reminder that the discussion period will end in less than 24 hours. We would appreciate it if you could take a moment to review authors' responses and provide any further comments before the discussion period closes.
Thank you for your time and effort!
Author Response (1/2): Risk Bound and Temporal Correction
Thank you for the constructive questions about what the bound explains and how the diagnostics can guide training.
Critical Weakness 1 · Question 1 · What the bound explains
Theorem 1 connects two properties of the OTTT-A update to finite-step hard-spike risk. Equation (18) separates the bias due to changing the spike trajectory from the bias due to approximating temporal backpropagation. In Eq. (13), these give the residuals 3LOTTT2Λδ2Tδ,K/μU and 3Dδ,K2/μU, respectively. This identifies which term is targeted by changing the forward spike model or the temporal gradient rule.
On CIFAR10-DVS, the soft temporal discrepancy Dδ2 averaged 358.95 across five final checkpoints. The observed hard–soft trajectory amplification had seed medians of 4.48–4.58 and a maximum of 7.46. These measurements quantify the temporal discrepancy and trajectory amplification at the tested checkpoints. Evaluating the numerical risk bound over training requires the averages in Eq. (12), uniform constants over the iterate region, and the threshold tail at the restricted comparator for the risk-transfer term. The membrane recurrence discussed in Q3 gives a sufficient condition for horizon-uniform amplification at fixed depth and with uniformly bounded layer operators.
A concrete sufficient case for PL is an affine readout on frozen features with a positive MSE weight and a positive-definite feature second moment (Karimi et al., 2016, Appendix B). Using a global lower bound on the soft risk in the descent argument behind Eq. (19) gives an averaged stationarity bound with variance and bias residuals (Ajalloeian & Stich, 2020, Sec. 4). Restricted PL converts this stationarity bound into the risk-gap comparison in Theorem 1.
Critical Weakness 2 · Question 2 · Does reducing the temporal gap improve training?
A targeted temporal correction improves mean final accuracy on CIFAR-10, CIFAR-100, and CIFAR10-DVS. We trained VGG11 with OTTT-A and with the two-step correction (h=2), using three paired seeds per dataset. Each pair shared the initialization and data seeds, hard-forward model, surrogate, input length, batch size, optimizer settings, and 300-epoch schedule. We report test accuracy from the final checkpoint at epoch 299.
On CIFAR10-DVS, where the temporal discrepancy dominates at the default setting, the correction increased mean final accuracy by 0.57 percentage points. This illustrates how the diagnostic can guide a targeted intervention with a measurable training benefit.
For each loss, the correction replaces the OTTT contributions from the most recent h lags with their SG-BPTT counterparts on the same hard trajectory. The original OTTT trace supplies the older contributions. The update is
Gh=GOTTT+GBPTT≤h−GOTTT≤h.
The subtraction removes the original window contribution before its replacement is added. The same-time contributions agree, so h=0 recovers OTTT-A and h=T−1 gives full SG-BPTT. In VGG11 training mode, synthetic-batch checks verified both endpoints and confirmed that the h=2 replay preserved stepwise logits. We will use final-checkpoint accuracy in Fig. 3(a) to match the diagnostic checkpoint.