Direct Optimization of a 3D Finite-Source Reflector via Neural-Network Parameterization

arXiv:2609.00899 · physics.optics, cs.LG · Submitted 2026-09-01 · Read on arXiv

physics.optics, cs.LG

Submitted: 2026-09-01

Updated: 2026-09-01

Comments: 16 pages, 4 figures, 2 tables. Submitted to Journal of the Optical Society of America A

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

Terminology

• Optimal Transport — 5× in this paper · explained in 5 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Objective Function — 3× in this paper · explained in 2 episodes
• Wasserstein Distance — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Neural-network methods for two-dimensional finite-source reflector design

Related papers

• Quantitative Benchmarking of Spectroscopic Homogeneous and Inhomogeneous Linewidth Separation
• Reciprocal asymmetric transmission in self-shadowed metallized gratings
• Method for SOFI-based spatial super-resolution in nanosensing with blinking emitters
• Confocal imaging from biphoton correlations
• Flexible Inverse Design of Optical Multilayer Coatings Using Discrete-Continuous Flow Matching
• Quantum-Limited Optical Vector Analysis