Tensor-network-based variational autoregressive networks (TNVAN) fix a small 'width set' of spins, contract the rest of the network exactly, and fit a neural variational distribution on the reduced system to estimate free energy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.stat-mech 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integrating Neural Networks and Tensor Networks for Computing Free Energy
Tensor-network-based variational autoregressive networks (TNVAN) fix a small 'width set' of spins, contract the rest of the network exactly, and fit a neural variational distribution on the reduced system to estimate free energy.