AI Paper Atlas

Research map / Optimization / Optimizers

High-Performance Real-World Optical Computing Trained by in Situ Gradient-Based Model-Free Optimization

Guangyuan Zhao, Xin Jian Shu, Renjie Zhou

TPAMI 2024 · Optimization › Optimizers · approach: Natural gradient and Fisher approximations · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use G-MFO instead of HBT for training under misalignmenttwo-layer optical system · MNIST (two-layer simulation)test accuracy: 78.4% -> 87.0%Improved
use G-MFO instead of HBT for training under misalignmenttwo-layer optical system · FMNIST (two-layer simulation)test accuracy: 59.8% -> 74.1%Improved
use G-MFO instead of HBT on the real single-layer systemsingle-layer optical system · MNIST (real single-layer experiment)test accuracy: 72.8% -> 73.6%Improved
use G-MFO instead of HBT on the real single-layer systemsingle-layer optical system · FMNIST (real single-layer experiment)test accuracy: 65.8% -> 70.4%Improved
fine-tune the HBT result with G-MFOsingle-layer optical system · MNIST (real single-layer experiment)test accuracy: 72.8% -> 77.7%Improved
fine-tune the HBT result with G-MFOsingle-layer optical system · FMNIST (real single-layer experiment)test accuracy: 65.8% -> 70.2%No clear effect
use HBT instead of SBT (in situ forward pass)single-layer optical system · MNIST (real single-layer experiment)test accuracy: 69.3% -> 72.8%Improved
use two-point ZO estimation instead of G-MFO sampling (ablation)zeroth-order optimizer · FMNIST (simulated single-layer, 100 samples)train accuracy: 99.0% -> 22.0%Hurt
use G-MFO instead of full-point ZOzeroth-order optimizer · FMNIST (simulated single-layer, 100 samples)training time per epoch: 113 min -> 2 minImproved
increase sampling size M from 32 to 128 (ablation)G-MFO · MNIST simulation (1,000 samples)training accuracy: +2.2%Improved
increase sampling size M from 128 to 256 (ablation)G-MFO · MNIST simulation (1,000 samples)training accuracy: +0.5%No clear effect
increase trainable parameters H beyond 128^2 at M=128 (ablation)G-MFO · MNIST simulation (1,000 samples)training accuracy: H > 128^2 with M=128Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy