A bounded-degree graph recurrent neural network, augmented with RBM-inspired correlators and a semistochastic energy estimator, reaches chemical accuracy for H50, an iron-sulfur cluster model, and a 3D H18 cluster.
Improved speed and scaling in orbital space variational Monte Carlo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.chem-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hybrid tensor network and neural network quantum states for quantum chemistry
A bounded-degree graph recurrent neural network, augmented with RBM-inspired correlators and a semistochastic energy estimator, reaches chemical accuracy for H50, an iron-sulfur cluster model, and a 3D H18 cluster.