Efficient representation of quantum many-body states with deep neural networks
Open Access
- 22 September 2017
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Communications
- Vol. 8 (1), 1-6
- https://doi.org/10.1038/s41467-017-00705-2
Abstract
Part of the challenge for quantum many-body problems comes from the difficulty of representing large-scale quantum states, which in general requires an exponentially large number of parameters. Neural networks provide a powerful tool to represent quantum many-body states. An important open question is what characterizes the representational power of deep and shallow neural networks, which is of fundamental interest due to the popularity of deep learning methods. Here, we give a proof that, assuming a widely believed computational complexity conjecture, a deep neural network can efficiently represent most physical states, including the ground states of many-body Hamiltonians and states generated by quantum dynamics, while a shallow network representation with a restricted Boltzmann machine cannot efficiently represent some of those states.This publication has 25 references indexed in Scilit:
- Solving the quantum many-body problem with artificial neural networksScience, 2017
- Deep learningNature, 2015
- The density-matrix renormalization group in the age of matrix product statesAnnals of Physics, 2011
- Simulating two- and three-dimensional frustrated quantum systems with string-bond statesPhysical Review B, 2010
- Representational Power of Restricted Boltzmann Machines and Deep Belief NetworksNeural Computation, 2008
- Matrix product states, projected entangled pair states, and variational renormalization group methods for quantum spin systemsAdvances in Physics, 2008
- Simulation of Quantum Many-Body Systems with Strings of Operators and Monte Carlo Tensor ContractionsPhysical Review Letters, 2008
- Criticality, the Area Law, and the Computational Power of Projected Entangled Pair StatesPhysical Review Letters, 2006
- Fault-tolerant quantum computation by anyonsAnnals of Physics, 2003
- A One-Way Quantum ComputerPhysical Review Letters, 2001