3 papers
cs.LG2026
Geodesic Gradient Descent: A Generic and Learning-rate-free Optimizer on Objective Function-induced Manifolds
Liwei Hu, Guangyao Li, Wenyong Wang +2
Euclidean gradient descent algorithms barely capture the geometry of objective function-induced hypersurfaces and risk driving update trajectories off the hypersurfaces. Riemannian…
physics.optics2025
Solving Distance-Based Optimization Problems Using Optical Hardware
Guangyao Li, Richard Zhipeng Wang, Natalia G. Berloff
We present a practical approach to solving distance-based optimization problems using optical computing hardware. The objective is to minimize an energy function defined as the wei…
physics.optics2025
Phase Retrieval via Gain-Based Photonic XY-Hamiltonian Optimization
Richard Zhipeng Wang, Guangyao Li, Silvia Gentilini +3
Phase-retrieval from coded diffraction patterns (CDP) is important to X-ray crystallography, diffraction tomography and astronomical imaging, yet remains a hard, non-convex inverse…