arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.04271cs.IRcs.DScs.LGquant-ph
收藏

一种基于量子理论的经典推荐算法

A quantum-inspired classical algorithm for recommendation systems

Ewin Tang

摘要:

我们给出了一个经典的模拟Kerenwald和Prakash的量子推荐系统,以前被认为是量子机器学习中可证明的指数加速的最强候选人之一。我们的主要结果是一个算法,给定一个$m \times n$矩阵的数据结构中支持某些$\ell^2$ -范数采样操作,输出一个$\ell^2$ -范数样本从秩$k$近似的矩阵在时间$O(\text{poly}(k)\log(mn))$,只有多项式慢于量子算法。因此,Kereneirs和Prakash的算法实际上并没有给出比经典算法更快的指数加速。此外,在强输入假设下,从我们的算法产生的经典推荐系统比以前的经典系统,运行在时间线性$m$和$n$指数更快地产生建议。这项工作的主要见解是使用简单的例程来操纵$\ell^2$ -范数采样分布,它在经典环境中发挥量子叠加的作用。这种对应关系表明了一个潜在的富有成效的框架,正式比较量子机器学习算法的经典机器学习算法。

英文摘要:

We give a classical analogue to Kerenidis and Prakash's quantum recommendation system, previously believed to be one of the strongest candidates for provably exponential speedups in quantum machine learning. Our main result is an algorithm that, given an $m \times n$ matrix in a data structure supporting certain $\ell^2$-norm sampling operations, outputs an $\ell^2$-norm sample from a rank-$k$ approximation of that matrix in time $O(\text{poly}(k)\log(mn))$, only polynomially slower than the quantum algorithm. As a consequence, Kerenidis and Prakash's algorithm does not in fact give an exponential speedup over classical algorithms. Further, under strong input assumptions, the classical recommendation system resulting from our algorithm produces recommendations exponentially faster than previous classical systems, which run in time linear in $m$ and $n$. The main insight of this work is the use of simple routines to manipulate $\ell^2$-norm sampling distributions, which play the role of quantum superpositions in the classical setting. This correspondence indicates a potentially fruitful framework for formally comparing quantum machine learning algorithms to classical machine learning algorithms.

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。

↑