Analog Optical Inference on Million-Record Mortgage Data
Sofia Berloff, Pavel Koptev, Konstantin Malkov
TLDR
This paper benchmarks an analog optical computer on a million-record mortgage dataset, identifying encoding and architectural limitations for accuracy.
Key contributions
- Benchmarked an analog optical computer (AOC) on 5.84M mortgage records for approval classification.
- AOC achieved 94.6% accuracy, 3.3pp lower than XGBoost, with architectural limits being key.
- Identified three sources of accuracy loss: data encoding, optical architecture, and hardware fidelity.
- Found hardware non-idealities imposed no measurable penalty on accuracy.
Why it matters
Analog optical computers offer efficiency but lack large-scale benchmarks. This paper provides the first million-record application, precisely locating where accuracy is lost across encoding, architecture, and hardware, guiding future improvements.
Original Abstract
Analog optical computers promise large efficiency gains for machine learning inference, yet no demonstration has moved beyond small-scale image benchmarks. We benchmark the analog optical computer (AOC) digital twin on mortgage approval classification from 5.84 million U.S. HMDA records and separate three sources of accuracy loss. On the original 19 features, the AOC reaches 94.6% balanced accuracy with 5,126 parameters (1,024 optical), compared with 97.9% for XGBoost; the 3.3 percentage-point gap narrows by only 0.5pp when the optical core is widened from 16 to 48 channels, suggesting an architectural rather than hardware limitation. Restricting all models to a shared 127-bit binary encoding drops every model to 89.4--89.6%, with an encoding cost of 8pp for digital models and 5pp for the AOC. Seven calibrated hardware non-idealities impose no measurable penalty. The three resulting layers of limitation (encoding, architecture, hardware fidelity) locate where accuracy is lost and what to improve next.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.