- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes enriched holomorphic neural networks for 2D and 3D Laplace problems with singularities. The method combines holomorphic networks with analytical singular functions and trainable singular exponents. It extends to 3D using independent networks along complex null directions. Experiments cover the closed-form, series reference, and application problems. Ablation studies examine singularity enrichment and training settings. The results show substantial accuracy improvements over tested baselines.
Critical strengths
-
The combination of the singularity enrichment dictionary, trainable singular exponents and the extension to three dimensions helps improve the general framework of solving Laplace problems with singularities. It is a theoretical advantage that the model satisfies the Laplace equation by construction.
-
The proposed methodology is evaluated across multiple experimental settings, including 2D and 3D singularity benchmarks, the randomized setups (24 instances, 72 paired runs). Experiments also show that the enrichment terms achieve more accurate solutions. The ablation on training budget and ladder depth also help explain the performance improvement.
Critical weaknesses
- The largest improvements are the ones that exact solutions can be represented directly by the supplied singular modes. In the CZT detector problem, the gains become substantially smaller, only 1.7\times+ over the next-best baselines. More evaluations of e.g. error variance, convergence rate across more random initializations, would strengthen the evidence of robustness.
Questions for authors
- Beyond the existing ablation studies, how does the solution error scale with network size and the number of singular enrichment terms across the 2D and 3D benchmarks? Does the same trend hold for problems whose exact solutions cannot be represented directly by the supplied singular modes?
2 comments
Thanks for the authors' responses, I will keep my initial score.
We thank the reviewer for their feedback and aim to address the weakness and question highlighted below.
Weakness 1: We agree that the largest improvements occur on problems whose solutions are supplied enrichment terms. We therefore also assessed problems where the network must represent a remainder. On Motz's problem and the cracked beam, adding the terms reduces the error by factors of 2.2×104 and 7.4×103, respectively (Table R2). In 3D, on uA, uB and extruded Motz, the error decreases by factors of 75–250 compared with the same model without the terms, and by a factor of 36 on the 3D detector (Table R2). On the 2D detector, the improvement is smaller, at a factor of 1.7, as discussed in Section 5.2. These results show that enrichment terms are also useful when they do not represent the entire solution.
To assess variance, we ran uA and uB with 20 seeds per model, each with three restarts. All 80 seed results, including failures, are retained in the medians and comparisons; no seed is dropped. With enrichment, the error lies between 9.6×10−5 and 2.2×10−4 on 39 of 40 seeds. The remaining run (uB, seed 8) has relative error 0.28 and boundary loss 0.16, compared with a boundary loss of at most 1.9×10−6 for the other runs. Without enrichment, 10 of 20 seeds on each problem finish with errors above 10−2, including 4 of 20 per problem with errors above 1. We believe these runs diverged, as their relative L2 errors are worse than predicting zero. On the 3D detector, the errors from our three seeds (1.1×10−2–1.5×10−2) do not overlap with those of the next-best methods (2.3×10−2 and above). These experiments assess final accuracy across seeds; they do not measure convergence rates during training.
Question 1: We ran additional scaling experiments on problems whose solutions are not sums of the supplied enrichment terms and observe the same trend. In 2D, we tested Motz's problem and the cracked beam with widths from 4 to 64 and 0 to 8 enrichment terms. Increasing network size alone does not improve accuracy: without enrichment, the error remains between 1.8×10−3 and 4.2×10−3 as the parameter count increases from 78 to 8,718. Adding the first term reduces the error by a factor of 90–300, and the second gives a further reduction by a factor of 6–450. With four terms, the error decreases as width increases. For example, on Motz's problem it decreases from 8.5×10−7 at width 4 to 6.0×10−8 at width 64. Using eight terms gives less accurate results than using four, with errors between 1.5×10−7 and 1.7×10−5. We do not yet have an explanation for this behavior.
In 3D, on uA, the error with enrichment remains near 1.8×10−4 across 4–32 branches, widths of 4–16, and one to four terms per edge. This limitation is consistent with the constant-amplitude edge terms, which restrict variation along the edge, as discussed in Section 6.2. Without enrichment, the best seed gives an error between 8.7×10−4 and 1.3×10−3 at every model size. However, at most sizes, one of the three seeds finishes with an error of 1.9×10−2 or above.