High-performance real-world optical computing trained by in situ model-free optimization

Optical computing systems provide high-speed and low-energy data processing but face deficiencies in computationally demanding training and simulation-to-reality gaps. We propose a model-free optimization (MFO) method based on a score gradient estimation algorithm for computationally efficient in situ training of optical computing systems. This approach treats an optical computing system as a black box and back-propagates the loss directly to the optical computing weights' probability distributions, circumventing the need for a computationally heavy and biased system simulation. Our experiments on a single-layer diffractive optical computing system show that MFO outperforms hybrid training on the MNIST and FMNIST datasets. Furthermore, we demonstrate image-free and high-speed classification of cells from their phase maps. Our method's model-free and high-performance nature, combined with its low demand for computational resources, expedites the transition of optical computing from laboratory demonstrations to real-world applications.