Abstract
We study the representational power of Boltzmann machines (a type of neural network) in quantum many-body systems. We prove that any (local) tensor network state has a (local) neural network representation. The construction is almost optimal in the sense that the number of parameters in the neural network representation is almost linear in the number of nonzero parameters in the tensor network representation. Despite the difficulty of representing (gapped) chiral topological states with local tensor networks, we construct a quasilocal neural network representation for a chiral -wave superconductor. These results demonstrate the power of Boltzmann machines.
- Received 20 July 2021
- Accepted 20 September 2021
DOI:https://doi.org/10.1103/PhysRevLett.127.170601
© 2021 American Physical Society