arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00054quant-phcs.DS
收藏

基于子空间状态的量子机器学习

Quantum machine learning with subspace states

Iordanis Kerenidis, Anupam Prakash

摘要:

介绍了一种基于量子子空间态的量子线性代数的新方法,并提出了三种新的量子机器学习算法。第一种是量子行列式采样算法,该算法使用$O(nd)$门和电路深度$O(d\log n)$从$|S|=d$的分布$\Pr[S]= det(X_{S}X_{S}^{T})$中采样。该任务的最新经典算法需要$O(d^{3})$操作\cite{derezinski2019minimax}。第二种是复合矩阵$\mathcal{A}^{k}$的量子奇异值估计算法,该算法的加速比是潜在指数的。它将一个$\binom{n}{k}$维的$k$阶相关向量分解为对应于$A$奇异向量的$k$元组的子空间状态的线性组合.第三种算法将用于量子拓扑数据分析的电路深度从$O(n)$指数级降低到$O(\log n)$。我们的基本工具是量子子空间态,定义为矩阵$X \in \mathbb{R}^{n \times d}$的$|Col(X)\rangle = \sum_{S\subset [n], |S|=d} det(X_{S}) |S\rangle$,使得$X^{T} X = I_{d}$,编码$\mathbb{R}^{n}$的$d$维子空间.我们开发了两种高效的状态准备技术,第一种使用Givens电路,将子空间表示为Givens旋转序列,而第二种使用具有$O(\log n)$深度电路(我们称之为Clifford加载器)的酉数$Γ(x) = \sum_{i} x_{i} Z^{\otimes (i-1)} \otimes X \otimes I^{n-i}$的高效实现。

英文摘要:

We introduce a new approach for quantum linear algebra based on quantum subspace states and present three new quantum machine learning algorithms. The first is a quantum determinant sampling algorithm that samples from the distribution $\Pr[S]= det(X_{S}X_{S}^{T})$ for $|S|=d$ using $O(nd)$ gates and with circuit depth $O(d\log n)$. The state of art classical algorithm for the task requires $O(d^{3})$ operations \cite{derezinski2019minimax}. The second is a quantum singular value estimation algorithm for compound matrices $\mathcal{A}^{k}$, the speedup for this algorithm is potentially exponential. It decomposes a $\binom{n}{k}$ dimensional vector of order-$k$ correlations into a linear combination of subspace states corresponding to $k$-tuples of singular vectors of $A$. The third algorithm reduces exponentially the depth of circuits used in quantum topological data analysis from $O(n)$ to $O(\log n)$. Our basic tool are quantum subspace states, defined as $|Col(X)\rangle = \sum_{S\subset [n], |S|=d} det(X_{S}) |S\rangle$ for matrices $X \in \mathbb{R}^{n \times d}$ such that $X^{T} X = I_{d}$, that encode $d$-dimensional subspaces of $\mathbb{R}^{n}$. We develop two efficient state preparation techniques, the first using Givens circuits uses the representation of a subspace as a sequence of Givens rotations, while the second uses efficient implementations of unitaries $Γ(x) = \sum_{i} x_{i} Z^{\otimes (i-1)} \otimes X \otimes I^{n-i}$ with $O(\log n)$ depth circuits that we term Clifford loaders.

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。

↑