Abstract

In gradient-based optimization of photonic devices, within the overall design parameter space, one iteratively performs a line search in a one-dimensional subspace as spanned by the search direction. While the search direction can be efficiently determined with the adjoint variable method, there has not been an efficient algorithm that determines the optimal learning rate that controls the distance one moves along the search direction. Here we introduce an efficient algorithm of determining the optimal learning rate, using the Shanks transformation in the Lippmann–Schwinger formalism. Our approach can determine very accurately the optimal learning rates at each epoch, with only a modest increase of computational cost. We show that this approach can significantly improve the figure of merits of the final structure, as compared to conventional methods for estimating the learning rate.

© 2020 Optical Society of America

Efficient method for accelerating line searches in adjoint optimization of photonic devices by combining Schur complement domain decomposition and Born series expansions

Nathan Z. Zhao, Salim Boutami, and Shanhui Fan
Opt. Express 30(4) 6413-6424 (2022)

Deep-learning-based image reconstruction for compressed ultrafast photography

Yayao Ma, Xiaohua Feng, and Liang Gao
Opt. Lett. 45(16) 4400-4403 (2020)

Optimization of an H0 photonic crystal nanocavity using machine learning

Ryotaro Abe, Taichi Takeda, Ryo Shiratori, Shinichi Shirakawa, Shota Saito, and Toshihiko Baba
Opt. Lett. 45(2) 319-322 (2020)

Modal-based nonlinear optimization algorithm for wavefront measurement with under-sampled data

Lei Zhao, Jian Bai, Yan Hao, Hou Jing, Chen Wang, Binjie Lu, Yiyong Liang, and Kaiwei Wang
Opt. Lett. 45(19) 5456-5459 (2020)

Optimal polarimeter structures for estimating polarization degree, angle, and ellipticity in the presence of additive noise

François Goudail and Jun Dai
Opt. Lett. 45(12) 3264-3267 (2020)