- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes KAPLAN-HR, a survival model based on Kolmogorov–Arnold Networks. It models event risk using patient characteristics and time, allowing interactions and effects that change over time. The authors provide a convergence analysis and evaluate the model on six clinical datasets.
Critical strengths
1- The paper provides a theoretical convergence result under clearly stated assumptions, rather than presenting only an application of an existing neural architecture.
2- The evaluation includes nine baseline methods, ten train–validation–test splits, and several prediction and calibration measures. The authors also acknowledge that the clinical results show competitive performance rather than clear superiority.
Critical weaknesses
1- The model-level novelty appears limited. The paper itself discusses earlier KAN-based survival models, including hazard regression. Although the theoretical analysis adds value, the methodological difference from the closest approaches should be explained more clearly.
2- The practical improvement is not convincing enough. KAPLAN-HR achieves the best survival prediction error and calibration score on only one of six datasets for each measure. None of the comparisons with the best-scoring baseline reaches statistical significance. These results support competitiveness, but leave the practical reason for choosing this model unclear.
3- The simulation comparison with GAM needs better control. KAPLAN-HR’s spline capacity increases with sample size, whereas the GAM uses fixed basis sizes. This could partly explain why GAM’s error stops improving in Figure 2. Allowing both models to increase their flexibility would make this comparison more informative.
4- The evidence for handling high-dimensional problems is narrow. The theoretical rate assumes that the true log-hazard has the specified smooth KAN representation. The higher-dimensional simulations keep only two informative variables and add noise variables. They therefore do not establish performance when many relevant variables interact.
Questions for authors
1- Does the advantage over GAM remain when its basis size also increases with the sample size?
2- Could the authors compare against a standard neural network using the same hazard formulation, training objective, and tuning budget to isolate the benefit of the KAN architecture?
3- How does the method perform when many covariates are informative or the true hazard does not follow the assumed KAN structure?
4 comments
Response (2/2)
Could the authors compare against a standard neural network using the same hazard formulation, training objective, and tuning budget to isolate the benefit of the KAN architecture?
We have added this comparison to both the simulations and the benchmark. MLP-HR replaces the KAN in KAPLAN-HR with a ReLU MLP on the concatenated input , keeping the same objective, training and prediction. In the simulations, each fit trains six MLP architectures (width × depth ) and keeps the one with the lowest validation NLL.
Median over repetitions of the paired ratio MLP-HR ÷ KAPLAN-HR (same training set), , , with 95% bootstrap intervals
| DGP-1 | DGP-2 | DGP-3 | DGP-4 |
|---|---|---|---|
| 4.35 [3.90, 5.28] | 0.61 [0.55, 0.67] | 0.81 [0.70, 0.99] | 1.32 [1.11, 1.49] |
On the same training set, MLP-HR attains a median of 4.35 times KAPLAN-HR's error on the additive DGP-1 and 1.32 times on the crossing-hazards DGP-4. It attains lower error on DGP-2 and DGP-3, where covariates interact, at 0.61 and 0.81 times.
On the benchmark, MLP-HR is tuned identically to the other models, with the same budget of 30 trials per split, over the same ranges as DeepSurv.
KAPLAN-HR against MLP-HR on the benchmark (mean over splits)
| KAPLAN-HR better | MLP-HR better | Significant (Holm ) | |
|---|---|---|---|
| C-TD | 4/6 | 2/6 | MIMIC-III, for KAPLAN-HR |
| IBS | 6/6 | 0/6 | FLCHAIN, for KAPLAN-HR |
| ICI | 4/6 | 2/6 | none |
The only significant differences are in C-TD on MIMIC-III and in IBS on FLCHAIN, where KAPLAN-HR attains the better value. Replacing the KAN with an MLP therefore does not improve predictive performance on the clinical benchmark.
We have added MLP-HR to the benchmarks (Table 1, Appendix F) and reported both comparisons in a new appendix (Appendix E.6).
How does the method perform when many covariates are informative or the true hazard does not follow the assumed KAN structure?
We have revised DGP-3 in the simulations (Figure 2) to test convergence with 32 interacting covariates. In this scenario, KAPLAN-HR's error descends more slowly than the theory's predicted rate from to , and at that rate from onward.
For a true hazard outside the assumed KAN structure, we have added an experiment fitting DGP-4 at hidden width 1 (Appendix E.4, p. 31). DGP-4 satisfies (C4) at hidden width but not at , since a width-1 network keeps the effect of relative to that of fixed over time, while in DGP-4 only the effect of reverses sign at .
Median over repetitions of the paired ratio width 1 ÷ width 3 on DGP-4 (same training set), , with 95% bootstrap intervals
| Width 1 ÷ width 3 | 0.90 [0.79, 1.01] | 1.14 [1.02, 1.34] | 3.26 [3.06, 3.90] |
The width-1 model attains 0.90 and 1.14 times the width-3 model's error at and . At larger its error flattens, reaching 3.26 times the width-3 model's error at , consistent with a remaining approximation error, while the width-3 model continues at the theory's rate (Appendix E.4). A violation of (C4) therefore manifested in this experiment as an error curve that flattens as grows.
Thank you for providing additional results. However, my main concern remains the limited novelty of the work.
Response
Thank you for providing additional results. However, my main concern remains the limited novelty of the work.
We thank the reviewer for their response. The key novelty of the paper lies in its statistical analysis of KAPLAN-HR. We clarify what was adopted and what is new.
- Adopted: The KAN architecture and choice of B-spline edge parameterisation (Liu et al., 2025), and the observation that B-spline KANs admit dimension-free approximation for compositions of smooth univariate edges (Liu et al., 2025). The rate machinery is the M-estimator rate theorem of van der Vaart and Wellner (2023, Thm 3.4.12). The strategy of establishing convergence bounds for neural survival estimators follows Deep Extended Hazards (Zhong et al., 2021) and Deep Partially Linear Transformations (Yin et al., 2025), and the choice of Hellinger distance as the metric follows Neural Frailty Machines (Wu et al., 2023).
- New: (i) A convergence analysis for a KAN parameterisation of the joint (x,t) log-hazard, which is the form that admits time-varying effects without a covariate-free baseline. (ii) Four proven propositions instantiating the rate theorem's hypotheses for a KAN sieve under right-censoring: an approximation bound for KANs of arbitrary depth, a bracketing entropy bound, a likelihood ratio bound, and a bracketing integral envelope of the shape the theorem requires. (iii) An extension of the rate theorem to an -near maximiser, traced through van der Vaart and Wellner (2023, Thm 3.4.1 and Lem 3.4.10). Training the non-convex objective via stochastic gradient methods does not deliver the exact sieve MLE, and the slack is required to account for this. (iv) The resulting rate, whose exponent depends only on the smoothness of the truth's KAN representation.
To our knowledge, no prior work has established a convergence rate for any KAN-based survival model.
Response (1/2)
We have made the comparison with the closest approaches explicit in the related work (lines 353–357). KAN survival models are distinguished by the structural restriction they place on the hazard. CoxKAN (Knottenbelt et al., 2025) and the model of Cheng and Hu (2025) place a KAN inside the proportional-hazards form, and KAN-AFT (Jose et al., 2025) imposes an accelerated failure time form. SurvKAN (Mastroleo et al., 2026) uses the same formulation as KAPLAN-HR, modelling the log-hazard as a KAN of the covariates and time trained on the full censored-data likelihood.
At the model level, KAPLAN-HR therefore differs from CoxKAN, the model of Cheng and Hu and KAN-AFT in the hazard structures it represents. Relative to SurvKAN, our contribution lies in the statistical analysis of the estimator. To our knowledge, no prior theoretical analysis has been conducted for any of these models.
To clarify when KAPLAN-HR is a suitable choice:
We have added this guidance to the conclusion (lines 495–502).
We have updated the simulations so the GAM's basis grows with the sample size. The spline basis of each covariate and of time now has kn=4Gn+4 functions, where Gn is KAPLAN-HR's number of grid intervals, so both models' capacity grows at the same rate.
Median over repetitions of the paired ISES ratio GAM ÷ KAPLAN-HR (same training set), R=20
With this adaptive basis, the GAM's error on the additive DGP-1 continues to descend across all n, where it previously plateaued, and is lower than KAPLAN-HR's at every n. On DGPs 2 to 4, the GAM's error still plateaus (Figure 2), and its ratio to KAPLAN-HR's grows from 1.09–2.04 at n=512 to 7.62–28.18 at n=65,536.