PreprintarXiv licencearXiv
Special Lagrangian cones in Deep Learning
Abstract
We introduce a matrix generalization of the cone of Harvey and Lawson and prove that it is an exact special Lagrangian manifold. We further show that it belongs to a family of exact special Lagrangian manifolds that foliate the balanced manifold arising in deep learning.
Related
- Uniqueness of tangent cones with immersed special Legendrian links
- Failure of Interior Hölder and Gradient Estimates for the Subcritical Special Lagrangian Equation
- Geometric regularity for semi-convex viscosity solutions to the special Lagrangian equation
- The exterior Dirichlet problem for special Lagrangian equations
- Sharp Small-Height Estimates for Subcritical Special Lagrangian Equations in Dimension Three
BibTeX
@misc{kotwal2026special,
title = {{Special Lagrangian cones in Deep Learning}},
author = {Tejas Kotwal and Govind Menon},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20159},
eprint = {2609.20159},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20159},
}
RIS
TY - UNPB
TI - Special Lagrangian cones in Deep Learning
AU - Tejas Kotwal
AU - Govind Menon
PY - 2026
DA - 2026/09/17
PB - arXiv
DO - 10.48550/arxiv.2609.20159
UR - https://arxiv.org/abs/2609.20159
AB - We introduce a matrix generalization of the cone of Harvey and Lawson and prove that it is an exact special Lagrangian manifold. We further show that it belongs to a family of exact special Lagrangian manifolds that foliate the balanced manifold arising in deep learning.
ER -