AG

Andrew Gracyk

cs.LGstat.MLcs.NAmath.DGmath.NAcond-mat.dis-nncs.AIcs.CVcs.SYeess.SY

On Valency

published · living versions

W_7smurv49·v1 · currentpublished

De Rham cohomological architectures for PINNs and PDEs with topological holes

1 version

Preprints & journals

9 papers in the corpus · 2022–2026

Shortcomings and capacities of real-constrained neural networks in complex spaces2606.04390v3 · Andrew Gracyk2026 · 0 citationsarXiv

Complex normalizing flows can almost be information Kähler-Ricci flows2604.17954v3 · Andrew Gracyk2026 · 0 citationsarXiv

Pseudo-differential-enhanced physics-informed neural networks2602.14663v3 · Andrew Gracyk2026 · 0 citationsarXiv

Inexact calculus of variations on the hyperspherical tangent bundle with connections to the attention mechanism2507.15431v5 · Andrew Gracyk2025 · 0 citationsarXiv

Geometric flow regularization in latent spaces for smooth dynamics with the efficient variations of curvature2506.09679v4 · Andrew Gracyk2025 · 0 citationsarXiv

Observability conditions for neural state-space models with eigenvalues and their roots of unity2504.15758v3 · Andrew Gracyk2025 · 0 citationsarXiv

Variational autoencoders with latent high-dimensional steady geometric flows for dynamics2410.10137v5 · Andrew Gracyk2024 · 0 citations23rd International Conference of Numerical Analysis and Applied Mathematics (ICNAAM) 2025

Ricci flow regularization in latent spaces for the forward learning of partial differential equations2401.14591v11 · Andrew Gracyk2024 · 1 citationarXiv

GeONet: a neural operator for learning the Wasserstein geodesic2209.14440v4 · Andrew Gracyk, Xiaohui Chen2022 · 0 citationsarXiv

Career total: 11 works. 9 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.