AI RESEARCH
Rethinking Neural Width for Alternating Current Optimal Power Flow Proxies
arXiv CS.LG
•
ArXi:2606.03125v1 Announce Type: new Deep learning proxies for Alternating Current Optimal Power Flow (ACOPF) lack systematic methods for determining architectural size. This paper conducts a constructive thought experiment to answer a fundamental inquiry: how wide must a neural network be to almost accurately approximate the ACOPF manifold? We