Abstract

We develop and apply a Bayesian linear regression technique for few-shot performance modeling of silicon photonic devices under process variation. The key contribution is to leverage information from low-fidelity simulations which are cheap to obtain, and to encode that information into the prior distribution under a Bayesian framework. We then evaluate the maximum-a-posteriori (MAP) estimator according to Bayes' theorem. Our numerical experiments on a rectangular waveguide and a Y-branch show that compared to linear regression, ridge regression, and a multi-layer feedforward neural network, this approach can achieve 7x smaller error given the same number of samples, or reduce running time by 2.4x to reach the same accuracy. Most importantly, we demonstrate that with only 10 expensive high-fidelity simulations and a small number of cheap low-fidelity simulations, our approach can obtain a model with good performance.

Process variation in silicon photonic devices

Xi Chen, Moustafa Mohamed, Zheng Li, Li Shang, and Alan R. Mickelson
Appl. Opt. 52(31) 7638-7647 (2013)

Inference of process variations in silicon photonics from characterization measurements

Zhengxing Zhang, Sally I. El-Henawy, Carlos A. Ríos Ocampo, and Duane S. Boning
Opt. Express 31(14) 23651-23661 (2023)

Bayesian color constancy

David H. Brainard and William T. Freeman
J. Opt. Soc. Am. A 14(7) 1393-1411 (1997)

A high performance photonic pulse processing device

David Rosenbluth, Konstantin Kravtsov, Mable P. Fok, and Paul R. Prucnal
Opt. Express 17(25) 22767-22772 (2009)

Availability estimation of optical network links using a Bayesian model

Filippos Christou
J. Opt. Commun. Netw. 16(5) B1-B15 (2024)