NNQS-Transformer: An Efficient and Scalable Neural Network Quantum States Approach for Ab Initio Quantum Chemistry

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 ab initio electronic structure calculati...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International Conference for High Performance Computing, Networking, Storage and Analysis (Online) s. 1 - 14
Hlavní autori: Wu, Yangjun, Guo, Chu, Fan, Yi, Zhou, Pengyu, Shang, Honghui
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: ACM 11.11.2023
Predmet:
Artificial neural networks
autoregressive sampling
Costs
Graphics processing units
High performance computing
many-body Schrödinger equation
neural network quantum state
Quantum chemistry
Scalability
Technological innovation
transformer based architecture
ISSN:2167-4337
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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 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.
ISSN:2167-4337
DOI:10.1145/3581784.3607061