English

Best Subset Selection: Statistical Computing Meets Quantum Computing

Methodology 2021-07-20 v1

Abstract

With the rapid development of quantum computers, quantum algorithms have been studied extensively. However, quantum algorithms tackling statistical problems are still lacking. In this paper, we propose a novel non-oracular quantum adaptive search (QAS) method for the best subset selection problems. QAS performs almost identically to the naive best subset selection method but reduces its computational complexity from O(D)O(D) to O(Dlog2D)O(\sqrt{D}\log_2D), where D=2pD=2^p is the total number of subsets over pp covariates. Unlike existing quantum search algorithms, QAS does not require the oracle information of the true solution state and hence is applicable to various statistical learning problems with random observations. Theoretically, we prove QAS attains any arbitrary success probability q(0.5,1)q \in (0.5, 1) within O(log2D)O(\log_2D) iterations. When the underlying regression model is linear, we propose a quantum linear prediction method that is faster than its classical counterpart. We further introduce a hybrid quantum-classical strategy to avoid the capacity bottleneck of existing quantum computing systems and boost the success probability of QAS by majority voting. The effectiveness of this strategy is justified by both theoretical analysis and extensive empirical experiments on quantum and classical computers.

Keywords

Cite

@article{arxiv.2107.08359,
  title  = {Best Subset Selection: Statistical Computing Meets Quantum Computing},
  author = {Wenxuan Zhong and Yuan Ke and Ye Wang and Yongkai Chen and Jinyang Chen and Ping Ma},
  journal= {arXiv preprint arXiv:2107.08359},
  year   = {2021}
}