neuralqx.experimental.driver package¶
Experimental VMC drivers in neuraLQX.
- class SingleTrunkMultiHeadVMC(variational_state, hamiltonian, optimizer, *, preconditioner=<netket.optimizer.preconditioner.IdentityPreconditioner object>, lambda_ortho=1.0, energy_weights=None, enforce_machine_pow_2=True, preconditioner_state_index=0)¶
Bases:
VMCVMC driver for a shared-parameter ST-MH ensemble built from head-specific
MCStateviews.The optimized objective is
\[C(\Theta) = \sum_k w_k E_k(\Theta) + \lambda \sum_{i<j} F_{ij}(\Theta),\]where
F_ijis the normalized pairwise fidelity estimator (formachine_pow=2). Thesum_{i<j}form is equivalent to(1/2) sum_{i!=j}used in the paper.The existing
MultiStateVMCis correct for MT-MH (independent parameter sets) and preconditions each state separately. This driver is for ST-MH. It aggregates all energy and penalty gradients into one shared parameter pytree and applies the optimizer/preconditioner exactly once.Note
The default
identity_preconditioneris exact for Euclidean gradient descent on the chosen Monte Carlo objective. If you pass an SR/QGT preconditioner, the driver applies it using a single reference head state’s geometry (preconditioner_state_index), which is a practical approximation.