NNQS-Transformer: an Efficient and Scalable Neural Network Quantum States Approach for Ab initio Quantum Chemistry
This work addresses computational bottlenecks in ab initio quantum chemistry for researchers, offering a scalable solution with demonstrated performance gains.
The paper tackles the high computational cost of neural network quantum states (NNQS) for quantum chemistry by developing an efficient and scalable method using a transformer-based wave function ansatz and parallelization schemes, achieving superior accuracy and scalability for systems with up to 120 spin orbitals.
Neural network quantum state (NNQS) has emerged as a promising candidate for quantum many-body problems, but its practical applications are often hindered by the high cost of sampling and local energy calculation. We develop a high-performance NNQS method for \textit{ab initio} electronic structure calculations. The major innovations include: (1) A transformer based architecture as the quantum wave function ansatz; (2) A data-centric parallelization scheme for the variational Monte Carlo (VMC) algorithm which preserves data locality and well adapts for different computing architectures; (3) A parallel batch sampling strategy which reduces the sampling cost and achieves good load balance; (4) A parallel local energy evaluation scheme which is both memory and computationally efficient; (5) Study of real chemical systems demonstrates both the superior accuracy of our method compared to state-of-the-art and the strong and weak scalability for large molecular systems with up to $120$ spin orbitals.