Special Lagrangian cones in Deep Learning

arXiv:2609.20159 · math.DG, cs.LG, math.SG · Submitted 2026-09-17 · Read on arXiv

math.DG, cs.LG, math.SG

Submitted: 2026-09-17

Updated: 2026-09-17

Comments: 16 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Deep Linear Network — 5× in this paper
• Generalization — 5× in this paper · explained in 13 episodes
• Gradient Flow — 3× in this paper · explained in 2 episodes
• Conservation Laws — 2× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• An entropy formula for the Deep Linear Network
• Regularization Implies balancedness in the deep linear network

Related papers

• Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks
• Barycentric subspace analysis of network-valued data