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.
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.
Neural Network Quantum States (NNQS) offer a powerful variational Monte Carlo (VMC) approach for quantum many-body problems, balancing polynomial scaling with high expressive power. However, scaling NNQS to large chemical systems faces challenges in preserving accuracy with exact energy and managing vast configurations efficiently. In this work, we introduce NNQS-SCI, a high-performance Selected Configuration Interaction (SCI) based NNQS method designed to overcome these limitations. NNQS-SCI employs highly parallelized Slater-Condon rules for fast local energy evaluations, avoiding accuracy loss, while its adaptive SCI engine dynamically manages billions of configurations without space explosion or arbitrary cutoffs that plague other NNQS-CI approaches. Optimized for extreme scalability via multi-level parallelism and memory compression, NNQS-SCI successfully simulates systems up to 152 spin orbitals, tackling Hilbert space dimensions exceeding 1014 and demonstrating significant advances in scale and efficiency. NNQS-SCI thus provides a robust and scalable path towards high-accuracy quantum chemistry on high-performance computing platforms.
The Neural Network Quantum States (NNQS) method is highly promising for accurately solving the Schrödinger equation, yet it encounters challenges such as computational demands and slow rates of convergence. To address the high computational requirements, we introduce optimizations including a cross-sample KV cache sharing technique to enhance sampling efficiency, Quantum Bitwise and BloomHash methods for more efficient local energy computation, and mixed-precision training strategies to boost computational efficiency. To overcome the issue of slow convergence, we propose a parallel training algorithm for NNQS under second quantization to accelerate the training of base models for molecular potential surfaces. Our approach achieves up to 27-fold acceleration specifically in local energy calculations in systems with 154 spin orbitals and demonstrates strong and weak scaling efficiencies of 98% and 97%, respectively, on the H2O2potential surface training set. The parallelized implementation of transformer-based NNQS is highly portable on various high-performance computing architectures, offering new perspectives on quantum chemistry simulations.
Solving quantum many-body problems is one of the fundamental challenges in quantum chemistry. While neural network quantum states (NQS) have emerged as a promising computational tool, its training process incurs exponentially growing computational demands, becoming prohibitively expensive for large-scale molecular systems and creating fundamental scalability barriers for real-world applications. To address the above challenges, we present QChem-Trainer, a highperformance NQS training framework for ab initio electronic structure calculations. First, we propose a scalable sampling parallelism strategy with multi-layer workload division and hybrid sampling scheme, which breaks the scalability barriers in large-scale NQS training. Second, we introduce multi-level energy calculation parallelism, enabling more efficient local energy computation in NQS training. Last, we employ cachecentric optimization for transformer-based ansatz and incorporate it with sampling parallelism strategy, which further accelerates the NQS training and achieves stable memory footprints at scale. Experiments demonstrate that QChem-Trainer provides up to8.41×speedup in NQS training and attains a parallel efficiency of up to 95.8% when scaling to 1,536 nodes.
Abstract Neural-network quantum states (NQS) has emerged as a powerful application of quantum-inspired deep learning for variational Monte Carlo methods, offering a competitive alternative to existing techniques for identifying ground states of quantum problems. A significant advancement toward improving the practical scalability of NQS has been the incorporation of autoregressive models, most recently transformers, as variational ansätze. Transformers learn sequence information with greater expressiveness than recurrent models, but at the cost of increased time complexity with respect to sequence length. We explore the use of the retentive network (RetNet), a recurrent alternative to transformers, as an ansatz for solving electronic ground state problems in ab initio quantum chemistry. Unlike transformers, RetNets overcome this time complexity bottleneck by processing data in parallel during training, and recurrently during inference. We give a simple computational cost estimate of the RetNet and directly compare it with similar estimates for transformers, establishing a clear threshold ratio of problem-to-model size past which the RetNet’s time complexity outperforms that of the transformer. Though this efficiency comes at the expense of decreased expressiveness relative to the transformer, we overcome this gap through training strategies that leverage the autoregressive structure of the model—namely, variational neural annealing. Our findings support the RetNet as a means of improving the time complexity of NQS without sacrificing accuracy. We provide further evidence that the ablative improvements of neural annealing extend beyond the RetNet architecture, suggesting it would serve as an effective general training strategy for autoregressive NQS.
Abstract Variational optimization of neural-network representations of quantum states has been successfully applied to solve interacting fermionic problems. Despite rapid developments, significant scalability challenges arise when considering molecules of large scale, which correspond to non-locally interacting quantum spin Hamiltonians consisting of sums of thousands or even millions of Pauli operators. In this work, we introduce scalable parallelization strategies to improve neural-network-based variational quantum Monte Carlo calculations for ab-initio quantum chemistry applications. We establish GPU-supported local energy parallelism to compute the optimization objective for Hamiltonians of potentially complex molecules. Using autoregressive sampling techniques, we demonstrate systematic improvement in wall-clock timings required to achieve coupled cluster with up to double excitations baseline target energies. The performance is further enhanced by accommodating the structure of resultant spin Hamiltonians into the autoregressive sampling ordering. The algorithm achieves promising performance in comparison with the classical approximate methods and exhibits both running time and scalability advantages over existing neural-network based methods.
We introduce an efficient approach to implement neural network quantum states (NNQS) as trial wave functions in auxiliary-field quantum Monte Carlo (AFQMC). NNQS are a recently developed class of variational ansätze capable of flexibly representing many-body wave functions, though they often incur a high computational cost during optimization. AFQMC, on the other hand, is a powerful stochastic projector approach for ground-state calculations, but it normally requires an approximate constraint via a trial wave function or trial density matrix, whose quality affects the accuracy. Recently, it has been shown (Xiao et al., arXiv2505.18519) that a broad class of highly correlated wave functions can be integrated into AFQMC through stochastic sampling techniques. In this work, we apply this approach and present a direct integration of NNQS with AFQMC, allowing NNQS to serve as high-quality trial wave functions for AFQMC with manageable computational cost. We test the NNQS-AFQMC method on the challenging nitrogen molecule (N 2 ) at stretched geometries. Our results demonstrate that AFQMC with an NNQS trial wave function can attain near-exact total energies, highlighting the potential of AFQMC with NNQS to overcome longstanding challenges in strongly correlated electronic structure calculations. We also outline future research directions for improving this promising methodology.