Black-box optimization for integer-variable problems using Ising machines and factorization machines
Keio University（庆应义塾大学）；National Institute for Materials Science（国立材料科学研究所）；The University of Tokyo（东京大学）；Waseda University（早稻田大学）；Tokyo Institute of Technology（东京工业大学）
Black-box optimization has potential in numerous applications such as hyperparameter optimization in machine learning and optimization in design of experiments. Ising machines are useful for binary optimization problems because variables can be represented by a single binary variable of Ising machines. However, conventional approaches using an Ising machine cannot handle black-box optimization problems with non-binary values. To overcome this limitation, we propose an approach for integer-variable black-box optimization problems by using Ising/annealing machines and factorization machines in cooperation with three different integer-encoding methods. The performance of our approach is numerically evaluated with different encoding methods using a simple problem of calculating the energy of the hydrogen molecule in the most stable state. The proposed approach can calculate the energy using any of the integer-encoding methods. However, one-hot encoding is useful for problems with a small size.
Surrogate Modeling via Factorization Machine and Ising Model with Enhanced Higher-Order Interaction Learning
Future Science and Technology Research Lab（未来科技研究实验室）；China Mobile (Suzhou) Software Technology Company Limited（中国移动（苏州）软件技术有限公司）；Graduate School of China Academy of Engineering Physics（中国工程物理研究院研究生部）；National Laboratory of Solid State Microstructures（固态微结构国家实验室）；School of Physics, Nanjing University（南京大学物理学院）；BrightGene Bio-Medical Technology Co., Ltd（BrightGene生物医学技术有限公司）
$L_0$ Regularization of Field-Aware Factorization Machine through Ising Model
Secure System Platform Research Laboratories, NEC Corporation（NEC公司安全系统平台研究所）；NEC-AIST Quantum Technology Cooperative Research Laboratories（NEC-AIST量子技术合作研究所）
Initialization Method for Factorization Machine Based on Low-Rank Approximation for Constructing a Corrected Approximate Ising Model
Graduate School of Science and Technology, Keio University（科技科学研究生院，庆应大学）；Recruit Co., Ltd.（Recruit公司）；Department of Applied Physics and Physico-Informatics, Keio University（应用物理与物理信息学系，庆应大学）；Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC), Keio University（庆应大学可持续量子人工智能中心（KSQAIC），庆应大学）；Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q), Keio University（人类生物学-微生物群-量子研究中心（WPI-Bio2Q），庆应大学）
High-Order Epistasis Detection Using Factorization Machine with Quadratic Optimization Annealing and MDR-Based Evaluation
Graduate School of Science and Technology（科学与技术研究生院）；Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC)（Keio大学可持续量子人工智能中心）；Keio University（Keio大学）；Department of Applied Physics and Physico-Informatics（应用物理与物理信息学系）；Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q)（人类生物学-微生物群-量子研究中心（WPI-Bio2Q））
Stage-dependent integer-binary encoding in factorization-machine black-box optimization
Graduate School of Science and Technology, Keio University（庆应义塾大学理工学研究科）；Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC), Keio University（庆应义塾大学可持续量子人工智能中心）；Department of Applied Physics and Physico-Informatics, Keio University（庆应义塾大学应用物理与物理信息学系）；Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q), Keio University（庆应义塾大学人类生物学-微生物组-量子研究中心）；Green Computing System Research Organization, Waseda University（早稻田大学绿色计算系统研究机构）
Global R$\&$D Center for Business by Quantum-AI Technology (G-QuAT), National Institute of Advanced Industrial Science and Technology (AIST)（量子人工智能技术商业研发中心（G-QuAT）、先进工业科学与技术国家研究所（AIST））；DENSO CORPORATION（DENSO公司）
Collaborative filtering based on nonnegative/binary matrix factorization
Department of Computer Science, Ochanomizu University, Tokyo, Japan（东京大学计算机科学系）；Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan（东芝公司研发中心）；Graduate School of Information Sciences, Tohoku University, Sendai, Japan（东北大学信息科学研究生院）
CoRMF: Criticality-Ordered Recurrent Mean Field Ising Solver
University of Rochester（罗切斯特大学）；Northwestern University（西北大学）；University of Maryland（马里兰大学）；National Center for Theoretical Sciences（国家理论科学中心）；HonHai (Foxconn) Research Institute（鸿海研究院）
SWIFT-FMQA: Enhancing Factorization Machine with Quadratic-Optimization Annealing via Sliding Window
Graduate School of Science and Technology, Keio University（Keio大学科学技术研究生院）；Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC)（Keio大学可持续量子人工智能中心）；Department of Applied Physics and Physico-Informatics, Keio University（Keio大学应用物理与物理信息学系）；Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q)（人类生物学-微生物组-量子研究中心）
Binary matrix factorization on special purpose hardware
University of Colorado Boulder（科罗拉多大学博尔德分校）；Fujitsu Research of America, Inc.（富士通美国研究院）
数据采掘中的许多基本问题可以归结为一个或多个NP难的组合优化问题。与使用通用计算机时相比，诸如量子和受量子启发的硬件之类的新技术的最新进展承诺了用于解决这些问题的显著加速，但是通常需要以特殊形式（诸如伊辛或二次无约束二进制优化（QUBO）模型）对问题进行建模，以便利用这些设备。在这项工作中，我们专注于重要的二进制矩阵分解（BMF）问题，有许多应用在数据采掘。我们提出了两个QUBO配方BMF。我们展示了如何聚类约束可以很容易地纳入这些配方。我们考虑的专用硬件在它可以处理的变量数量上是有限的，这在分解大型矩阵时提出了挑战。我们提出了一种基于采样的方法来克服这一挑战，使我们能够因式分解大型矩形矩阵。除了这些方法之外，我们还提出了一个简单的基线算法，它在某些情况下优于我们更复杂的方法。我们在Fujitsu Digital Annealer（一种量子启发的互补金属氧化物半导体（CMOS）退火机）上对合成和真实数据（包括基因表达数据）进行了实验。这些实验表明，我们的方法是能够产生更准确的BMF比竞争的方法。
