Machine learning framework for quantum sampling of highly constrained, continuous optimization problems

Abstract

In the recent years, there is a growing interest in using quantum computers for solving combinatorial optimization problems. In this work, we developed a generic, machine learningbased 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.

Optimizing Startshot Lightsail Design: A Generative Network-Based Approach

“…Previously, it has been demonstrated that autoencoder-assisted inverse design frameworks can be efficiently applied to multi-objective optimization problems. These approaches could be used for global optimization via hybridization with different heuristics algorithms, , including frameworks that allow sampling globally optimized solutions by leveraging classical and quantum quadratic unconstrained binary optimization solvers . The developed VAE-TO framework opens the way to realize the multi-objective optimization of the lightsail design employing the previously proven concept of physics-driven compressed space engineering …”

Quantum Annealing Designs Nonhemolytic Antimicrobial Peptides in a Discrete Latent Space

“…What makes a QA attractive is the theoretical guarantee of finding the global optimal solution under the assumption of ideal qubits and slow annealing . Although this goal is not attainable currently, recent successful case studies in materials science , imply that the quality of qubits has improved to the point that they are practically useful. In addition, QA-based methods are likely to benefit from future development of quantum technologies.…”

Spatial-photonic Boltzmann machines: low-rank combinatorial optimization and statistical learning by spatial light modulation

“…A necessity for solving low-rank Ising problems arises when we consider the learning of combinatorial optimization problems [41][42][43]. For example, in a study on the automated design of metamaterials [41], the authors train a factorization machine [44], which has a low-rank quadratic form similar to the SPBM Hamiltonian, and find low-energy candidates for metamaterials using a D-Wave quantum annealer.…”