Quantum machine learning with subspace states
(2202.00054)Abstract
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 $\Gamma(x) = \sum{i} x_{i} Z{\otimes (i-1)} \otimes X \otimes I{n-i}$ with $O(\log n)$ depth circuits that we term Clifford loaders.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.