AI RESEARCH
Classical and Quantum Speedups for Non-Convex Optimization via Energy Conserving Descent
arXiv CS.LG
•
ArXi:2604.13022v1 Announce Type: cross The Energy Conserving Descent (ECD) algorithm was recently proposed (De Luca & Silverstein, 2022) as a global non-convex optimization method. Unlike gradient descent, appropriately configured ECD dynamics escape strict local minima and converge to a global minimum, making it appealing for machine learning optimization. We present the first analytical study of ECD, focusing on the one-dimensional setting for this first installment.