arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02355cs.LGphysics.data-anstat.ML
收藏

绝热量子线性回归

Adiabatic Quantum Linear Regression

Oak Ridge National Laboratory(橡树岭国家实验室)

Prasanna Date, Thomas Potok

摘要:

机器学习的一个主要挑战是训练这些模型的计算开销。模型训练可以被视为一种优化形式,用于将机器学习模型拟合到一组数据,这在经典计算机上可能会占用大量时间。绝热量子计算机已被证明擅长解决优化问题,因此,我们相信,它是改善机器学习训练时间的一种有前途的替代方案。在本文中,我们提出了一种绝热量子计算方法来训练线性回归模型。为了做到这一点,我们制定的回归问题作为一个二次无约束二元优化(QUBO)问题。我们从理论上分析了我们的量子方法,在D-Wave 2000 Q绝热量子计算机上进行了测试,并将其性能与使用Python中Scikit-learn库的经典方法进行了比较。我们的分析表明,量子方法在更大的数据集上比经典方法获得了高达2.8倍的加速,并且在回归误差度量上与经典方法不相上下。

英文摘要:

A major challenge in machine learning is the computational expense of training these models. Model training can be viewed as a form of optimization used to fit a machine learning model to a set of data, which can take up significant amount of time on classical computers. Adiabatic quantum computers have been shown to excel at solving optimization problems, and therefore, we believe, present a promising alternative to improve machine learning training times. In this paper, we present an adiabatic quantum computing approach for training a linear regression model. In order to do this, we formulate the regression problem as a quadratic unconstrained binary optimization (QUBO) problem. We analyze our quantum approach theoretically, test it on the D-Wave 2000Q adiabatic quantum computer and compare its performance to a classical approach that uses the Scikit-learn library in Python. Our analysis shows that the quantum approach attains up to 2.8x speedup over the classical approach on larger datasets, and performs at par with the classical approach on the regression error metric.

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。

↑