Natural evolution strategies and variational Monte Carlo. Issue 2 (29th December 2020)

• Record Type: Journal Article
• Authors: Zhao, Tianchen; Carleo, Giuseppe; Stokes, James; Veerapaneni, Shravan
• Is Part Of: Machine learning: science and technology. Volume 2:Issue 2(2021)
• Publication Date: 2020-12-29
• Subjects: machine learning -- variational quantum algorithms -- quantum; 006.31
• DOI: 10.1088/2632-2153/abcb50
• Languages: English
• ISSNs: 2632-2153

Abstract

Abstract: A notion of quantum natural evolution strategies is introduced, which provides a geometric synthesis of a number of known quantum/classical algorithms for performing classical black-box optimization. The recent work of Gomes et al (2019 arXiv:1910.10675) on heuristic combinatorial optimization using neural quantum states is pedagogically reviewed in this context, emphasizing the connection with natural evolution strategies (NES). The algorithmic framework is illustrated for approximate combinatorial optimization problems, and a systematic strategy is found for improving the approximation ratios. In particular, it is found that NES can achieve approximation ratios competitive with widely used heuristic algorithms for Max-Cut, at the expense of increased computation time.