Classical and Quantum Algorithms for Tensor Principal Component Analysis
arXiv:1907.12724 · doi:10.22331/q-2020-02-27-237
Abstract
We present classical and quantum algorithms based on spectral methods for a problem in tensor principal component analysis. The quantum algorithm achieves a quartic speedup while using exponentially smaller space than the fastest classical spectral algorithm, and a super-polynomial speedup over classical algorithms that use only polynomial space. The classical algorithms that we present are related to, but slightly different from those presented recently in Ref. 1. In particular, we have an improved threshold for recovery and the algorithms we present work for both even and odd order tensors. These results suggest that large-scale inference problems are a promising future application for quantum computers.
arXiv comment29 pages; v2 accepted in Quantum
References in corpus (10)
- Hamiltonian Simulation by Qubitization
- Optimal Hamiltonian Simulation by Quantum Signal Processing
- Simulating Hamiltonian dynamics with a truncated Taylor series
- Hamiltonian simulation with nearly optimal dependence on all parameters
- Solving strongly correlated electron models on a quantum computer
- Exponential improvement in precision for simulating sparse Hamiltonians
- Fast linear algebra is stable
- Statistical and computational phase transitions in spiked tensor estimation
- Ground States of Fermionic lattice Hamiltonians with Permutation Symmetry
- The Asymptotics of Quantum Max-Flow Min-Cut