Aspects of the present disclosure describe a method including predicting a first set of ansatz terms and a first plurality of amplitudes associated with the first set of ansatz terms; minimizing energy of the system based on the first set of ansatz terms and the first plurality of amplitudes; computing perturbative corrections using one or more ansatz wavefunctions; determining whether energy of the system converges; and predicting, in response to determining that the energy of the system does not converge, a second set of ansatz terms and a second plurality of amplitudes associated with the second set of ansatz terms.
展开▼