- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposed HiPPO-FM to map irregular sequential data to fixed rank and a resuable coordinate-addressable state. It applies self-attention before writing observations into kernel-smoothed Legendre coordinates, then it uses a matched Gram solve for coordinate evaluation. The experiments showed improved performance on continuous coordinate reconstructions.
Critical strengths
- The experiments covers different task types and reports results across multiple seeds.
- The RKHS analysis clearly discussed exact functional values and learned normalized memory, and the stated proofs is sound.
Critical weaknesses
- The below paper [1] is very relevant but not cited. Its HiPPO–Legendre interdomain covariances and predictive mean correspond to the continuous counterparts of the kernel geometry and readout in Eq. (5)–(9) of this submission. The authors should justify the novelty.
[1] Chen, Wenlong, Naoki Kiyohara, Harrison Zhu, Jacob Curran-Sebastian, Samir Bhatt, and Yingzhen Li. "Recurrent memory for online interdomain gaussian processes." Advances in Neural Information Processing Systems 38 (2026): 134836-134873.
-
There is no ablation study to proof that whether the gains come from self-attention, the Legendre features, or the matched Gram readout.
-
The event prediction experiments didn't define the conditional intensity or density, likelihood computation, prediction heads, or training objective.
Questions for authors
Please see Weaknesses section and consider each point as a question.
Response to Reviewer dxs7
We thank the reviewer for identifying the missing attribution to OHSVGP (Chen et al., 2025) and raising questions about novelty, ablations, and reproducibility. We revised the manuscript to clarify the mathematical foundations, architecture, and experimental protocol.
Q1. Missing citation of Chen et al. (2025) and methodological novelty.
We added citations and discussion in the Introduction, Section 2, Section 3.2, and Appendix B.1.
Mathematical connection. Both methods use HiPPO–Legendre functionals and kernel-induced interdomain geometry:
The HiPPO–Legendre functionals and inverse-Gram readout follow constructions established in OHSVGP. HiPPO-FM incorporates this geometry into a deterministic, end-to-end trained memory architecture. Its encoder applies self-attention over the observed support, writes content-updated values into a fixed-rank state, and evaluates the retained coefficients at arbitrary temporal coordinates. The memory stores learned neural values, whereas OHSVGP maintains a variational GP posterior. Interdomain Attention updates basis coefficients through SSM recurrence; HiPPO-FM forms its state through a single write after observed-support interaction. ContiFormer evaluates observation-dependent representations at requested times, whereas HiPPO-FM reuses the same encoded state across coordinate queries.
Q2. Ablation evidence.
We added five-seed ablations on Spiral reconstruction (Section 4.5, Table 5; Appendix D).
RMSE: mean ± sample SD, in units of 10−2; lower is better.
Removing encoder FM while retaining MHA, layer normalization, and FFN increases RMSE substantially (paired t-test p=3.5×10−6; exact Wilcoxon p=0.0625).
Q3. Event-prediction protocol.
We expanded Section 4.3 and Appendix A.4 with the model architecture, conditional intensity, likelihood, prediction rules, and training objective.
Architecture. HiPPO-FM replaces only the history encoder in the ContiFormer reference implementation; event embedding, prediction head, likelihood, and loss are retained. Each marked event (tj,kj) is embedded, processed over support {tj}, and passed through the reference single-layer LSTM to obtain hj.
Conditional intensity and likelihood:
\operatorname{softplus}_{\beta_k} (w_k^\top h_j+b_k+\alpha_k(t-t_j)), \quad \lambda=\sum_k\lambda_k,$$ where $\operatorname{softplus}_{\beta}(x)=\beta^{-1}\log(1+e^{\beta x})$. $$\begin{aligned} \log\mathcal L &=\sum_j\log\lambda_{k_{j+1}}(t_{j+1}\mid\mathcal H_{t_j}) -\sum_j\int_{t_j}^{t_{j+1}}\lambda(s\mid\mathcal H_{t_j})\,ds,\\ p_j(\tau) &=\lambda(t_j+\tau)\exp\left(-\int_0^\tau\lambda(t_j+s)\,ds\right),\\ \hat\tau_{j+1} &=\int_0^{t_{\max}}\tau p_j(\tau)\,d\tau,\\ \hat k_{j+1} &=\arg\max_k\int_0^{t_{\max}} \frac{\lambda_k(t_j+\tau)}{\lambda(t_j+\tau)}p_j(\tau)\,d\tau. \end{aligned}$$ The intensity integral uses a uniform grid with step 0.01; predictions use the trapezoidal rule. **Training objective:** $$\mathcal{J}=-\log\mathcal{L}+\gamma^{\mathrm{mark}}\operatorname{CE}(\hat{k},k)+(\gamma^{\mathrm{time}})^{-1}\sum(\hat{\tau}(j+1)-\tau(j+1))^2$$ Here, CE uses label smoothing of 0.1, and the sum is over events. The reference configuration uses $t_{\max}=5$, $\gamma^{\mathrm{mark}}=1$, and $\gamma^{\mathrm{time}}=100$.