Natural evolution strategies and variational Monte Carlo

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. Recent work of Gomes et al. [2019] on heuristic combinatorial optimization using neural quantum states is pedagogically reviewed in this context, emphasizing the connection with natural evolution strategies. 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 natural evolution strategies can achieve approximation ratios competitive with widely used heuristic algorithms for Max-Cut, at the expense of increased computation time.

References in corpus (7)

• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Theory of variational quantum simulation
• Green Function Monte Carlo with Stochastic Reconfiguration
• Low-rank optimization for semidefinite convex problems
• NetKet: A Machine Learning Toolkit for Many-Body Quantum Systems
• Expressive Power and Approximation Errors of Restricted Boltzmann Machines
• Probabilistic Modeling with Matrix Product States

Cited by in corpus (11)

• Noisy intermediate-scale quantum (NISQ) algorithms
• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• Near-Term Quantum Computing Techniques: Variational Quantum Algorithms, Error Mitigation, Circuit Compilation, Benchmarking and Classical Simulation
• A comprehensive review of Quantum Machine Learning: from NISQ to Fault Tolerance
• Automatic design of quantum feature maps
• Natural Evolutionary Strategies for Variational Quantum Computation
• Supplementing Recurrent Neural Networks with Annealing to Solve Combinatorial Optimization Problems
• Random coordinate descent: a simple alternative for optimizing parameterized quantum circuits
• Qudit-inspired optimization for graph coloring
• Random Natural Gradient
• A NEAT Quantum Error Decoder