Paperlane

no. 4 · Wednesday 28 October 2026

Geometric priors for single-patch neural Calabi–Yau metrics on the quintic: a conservative fixed-$ψ$ Ablation study

D Yang Eng

math.AG

Abstract

We investigate how geometric priors shape neural approximations of the complex Monge–Amp`ere equation on the quintic Calabi–Yau threefold. This fixed-$ψ$ diagnostic compares four single-patch ans"atze: a coordinate SIREN potential model, a direct-metric Cholesky baseline, an algebraic section ansatz, and a section-plus-neural hybrid. In a 96-run learning-rate and frequency archive, section-based models reach validation $σ=4.14$--$4.16%$, whereas SIREN and Cholesky remain at $41.29%$ and $44.27%$. Multi-seed controls use a shared affine-$η$ evaluator and five fresh validation clouds. Stable section settings give $3.84$--$4.77%$, compared with $28.46$--$30.59%$ for Cholesky and $34.73$--$38.13%$ for SIREN. Hybrid projective features do not improve best-case accuracy, but they stabilise the stressed regime. They limit $σ$ to $4.26$--$4.41%$, versus $4.45$--$205.45%$ for raw coordinates. Within this protocol, section-based geometric structure is the main driver of accuracy; coordinate-only models plateau at substantially higher error, and raw hybrid flexibility can amplify instability. We provide a projective-scaling derivation, document protocol asymmetries, and identify projectively consistent hybrid corrections as the next step.

journal
2026 Mach. Learn.: Sci. Technol. 7 035049
fields
Algebraic Geometry
pdf ↗ page arXiv:2610.35920 ↗