Treffer: Artifact of AccelerQ: Accelerating Quantum Eigensolvers With Machine Learning on Quantum Simulators

This repository is a public version of the KCL_QAGC project, which is actively under development. This artifact contains the code and data related to AccelerQ: Accelerating Quantum Eigensolvers With Machine Learning on Quantum Simulators paper. As AccelerQ takes as input quantum programs crafted by others with data coming from other datasets, we wish to note that these are not our data or code. The majority of it is taken from QAGC with ML Implementation at GitHub. The rest is extracted using other papers that are already cited in the publication. Abstract. AccelerQ is a framework for automatically tuning quantum eigensolver (QE) implementations–these are quantum programs implementing a specific QE algorithm–using machine learning and search-based optimisation. Rather than redesigning quantum algorithms or optimising the implementation of an already existing algorithm, AccelerQ treats QE implementations as black-box programs and learns to optimise their hyperparameters to improve accuracy and efficiency.Our approach leverages two key insights: (1) training on data extracted from smaller and simpler QE implementations’ inputs, and (2) training a program-specific machine learning (ML) model. To further enhance our approach, we incorporate search-based techniques and genetic algorithms (GA) alongside ML models to efficiently explore the hyperparameter space of QE implementations and avoid local minima. Our Contribution. AccelerQ is a set of Python programs for Data augmentation - kcl_prepare_data.py, with two wrappers for each QE implementation: kcl_QCELS_stage_1.py and kcl_adapt_vqe_stage_1.py. Training ML models - kcl_train_xgb.py, with two wrappers for each QE implementation: kcl_QCELS_stage_2.py and kcl_adapt_vqe_stage_2.py. Deploying the models - kcl_opt_xgb.py, with two wrappers for each QE implementation: kcl_QCELS_stage_3.py and kcl_adapt_vqe_stage_3.py. We then collected the new hyperparameter values and added them to the QE implementations: first_answer_experiments-tests.py and ...