Machine learning framework for quantum sampling of highly constrained, continuous optimization problems
Machine learning framework for quantum sampling of highly constrained, continuous optimization problems
复制标题
DOI：
10.1063/5.0060481
复制
发表时间：
2021-05
影响因子：
15
通讯作者：
Blake A. Wilson;Z. Kudyshev;A. Kildishev;S. Kais;V. Shalaev;A. Boltasseva
中科院分区：
文献类型：
--
作者：
Blake A. Wilson;Z. Kudyshev;A. Kildishev;S. Kais;V. Shalaev;A. Boltasseva
近年来，人们对使用量子计算机解决组合优化问题越来越感兴趣。在这项工作中，我们开发了一个基于机器学习的通用框架，通过采用二元变分自动编码器和分解机，将连续空间逆设计问题映射到代理二次无约束二元优化（QUBO）问题。分解机被训练为连续设计空间的低维二元代理模型，并使用各种 QUBO 采样器进行采样。使用 D-Wave Advantage 混合采样器和模拟退火，我们证明，通过对分解机进行重复重新采样和重新训练，我们的框架发现设计的品质因数超过了其训练集的品质因数。我们通过优化（i）用于热光伏应用的热发射器拓扑和（ii）用于高效光束控制的衍射元光栅来展示该框架在两个逆设计问题上的性能。该技术可以进一步扩展，以利用量子优化的未来发展来解决科学和工程应用的高级逆向设计问题。
In recent years, there is a growing interest in using quantum computers for solving combinatorial optimization problems. In this work, we developed a generic, machine learning-based framework for mapping continuous-space inverse design problems into surrogate quadratic unconstrained binary optimization (QUBO) problems by employing a binary variational autoencoder and a factorization machine. The factorization machine is trained as a low-dimensional, binary surrogate model for the continuous design space and sampled using various QUBO samplers. Using the D-Wave Advantage hybrid sampler and simulated annealing, we demonstrate that by repeated resampling and retraining of the factorization machine, our framework finds designs that exhibit figures of merit exceeding those of its training set. We showcase the framework's performance on two inverse design problems by optimizing (i) thermal emitter topologies for thermophotovoltaic applications and (ii) diffractive meta-gratings for highly efficient beam steering. This technique can be further scaled to leverage future developments in quantum optimization to solve advanced inverse design problems for science and engineering applications.