AI RESEARCH

Analog Optical Inference on Million-Record Mortgage Data

arXiv CS.LG

ArXi:2604.13251v1 Announce Type: new Analog optical computers promise large efficiency gains for machine learning inference, yet no nstration has moved beyond small-scale image benchmarks. We benchmark the analog optical computer (AOC) digital twin on mortgage approval classification from 5.84M U. S. HMDA records and separate three sources of accuracy loss.