量子机器学习的GPU加速近似核方法
GPU-Accelerated Approximate Kernel Method for Quantum Machine Learning
摘要:
传统的从头算势能面的基于核的机器学习模型,虽然在小数据范围内是准确和方便的,但随着训练集大小的增加,会产生巨大的计算成本。我们引入了QML-Lightning,这是一个包含GPU加速近似内核模型的PyTorch包,它将训练时间减少了几个数量级,在几秒钟内生成训练模型。QML-Lightning包括一个具有成本效益的FCHL 19 GPU实现,它可以在微秒/原子的时间尺度上以具有竞争力的精度产生能量和力预测。使用现代GPU硬件,我们报告了能量和力的学习曲线以及时间,作为从原子模拟(包括QM 9,MD-17和3BPA)中选择传统基准的数值证据。
英文摘要:
Conventional kernel-based machine learning models for ab initio potential energy surfaces, while accurate and convenient in small data regimes, suffer immense computational cost as training set sizes increase. We introduce QML-Lightning, a PyTorch package containing GPU-accelerated approximate kernel models, which reduces the training time by several orders of magnitude, yielding trained models within seconds. QML-Lightning includes a cost-efficient GPU implementation of FCHL19, which together can yield energy and force predictions with competitive accuracy on a microsecond-per-atom timescale. Using modern GPU hardware, we report learning curves of energies and forces as well as timings as numerical evidence for select legacy benchmarks from atomisitic simulation including QM9, MD-17, and 3BPA.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。