Scaling Laws for Neural-Network Quantum States

• URL: http://arxiv.org/abs/2606.02794v1
• Date: Mon, 01 Jun 2026 18:59:01 GMT
• Title: Scaling Laws for Neural-Network Quantum States
• Abstract summary: Scaling laws offer a way to characterize the complexity of a learning problem.<n>We show that scaling laws can be used to benchmark variational anstze.
• Score: 35.51694331707922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Scaling laws, the power-law relations between loss, architecture size, and compute observed in modern neural networks, offer a quantitative way to characterize the complexity of a learning problem, with the exponent governing the decay of the loss reflecting how rapidly additional resources translate into improved accuracy, and thus how hard the target is to learn. Whether an analogous framework can characterize the complexity of physical problems remains open. We address this question for Neural-Network Quantum States, a leading variational approach for strongly correlated quantum many-body systems. Using transformer wave functions to approximate ground states of the $J_1$-$J_2$ Heisenberg model on triangular and square lattices with up to $20\times 20$ sites, we find that the $V$-score, a measure of accuracy of a variational state, decays as a power law in training compute. Under an appropriate rescaling of compute, results for different system sizes collapse onto a single curve, analogous to scaling collapse in critical phenomena. The resulting power law is, to a good approximation, independent of the number of sites, showing that the transformer Ansatz is size-consistent for the systems considered. The exponent decreases systematically with frustration, identifying it as a quantitative measure of representational difficulty of the ground state and establishing scaling laws as a general framework for benchmarking variational ansätze.

Related papers

• Quantum-classical crossover in fault-tolerant quantum dynamics simulation [56.198154828333685]
  We introduce a scalable fault-tolerant framework that combines coherent observable estimation with a space-time-efficient implementation of non-Clifford rotations.<n>A benchmark against state-of-the-art tensor-network and variational Monte Carlo algorithms reveals a concrete crossover for mixed-field Ising dynamics.
  arXiv  Detail & Related papers  (2026-07-17T16:54:25Z)
• Information-Theoretic Scaling Laws of Neural Quantum States [6.378700750938894]
  We show that exact autoregressive representation of a quantum state requires the virtual-bond dimension to scale with the amplitude mutual information.<n>For stabilizer-state families, we show that this law yields an explicit, analytical rank formula.
  arXiv  Detail & Related papers  (2026-03-24T17:34:26Z)
• Solving excited states for long-range interacting trapped ions with neural networks [4.294084794573824]
  We introduce a neural network-based algorithm that simultaneously output multiple low-lying excited states of a quantum many-body spin system.<n>The NQES algorithm is capable of efficiently computing multiple excited states and their related observable expectations.<n>Our results establish a scalable and efficient algorithm for computing excited states of interacting quantum many-body systems.
  arXiv  Detail & Related papers  (2025-06-10T09:02:59Z)
• Retentive Neural Quantum States: Efficient Ansätze for Ab Initio Quantum Chemistry [10.423935999935315]
  We explore the use of the retentive network (RetNet) as an ansatz for solving electronic ground state problems in quantum chemistry. We show that RetNet overcomes this time complexity bottleneck by processing data in parallel during training, and recurrently during inference.
  arXiv  Detail & Related papers  (2024-11-06T13:24:34Z)
• Solving reaction dynamics with quantum computing algorithms [42.408991654684876]
  We study quantum algorithms for response functions, relevant for describing different reactions governed by linear response.<n>We focus on nuclear-physics applications and consider a qubit-efficient mapping on the lattice, which can efficiently represent the large volumes required for realistic scattering simulations.
  arXiv  Detail & Related papers  (2024-03-30T00:21:46Z)
• Scalable Imaginary Time Evolution with Neural Network Quantum States [0.0]
  The representation of a quantum wave function as a neural network quantum state (NQS) provides a powerful variational ansatz for finding the ground states of many-body quantum systems. We introduce an approach that bypasses the computation of the metric tensor and instead relies exclusively on first-order descent with Euclidean metric. We make this method adaptive and stable by determining the optimal time step and keeping the target fixed until the energy of the NQS decreases.
  arXiv  Detail & Related papers  (2023-07-28T12:26:43Z)
• Towards Neural Variational Monte Carlo That Scales Linearly with System Size [67.09349921751341]
  Quantum many-body problems are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors. The combination of neural networks (NN) for representing quantum states, and the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems. We propose a NN architecture called Vector-Quantized Neural Quantum States (VQ-NQS) that utilizes vector-quantization techniques to leverage redundancies in the local-energy calculations of the VMC algorithm.
  arXiv  Detail & Related papers  (2022-12-21T19:00:04Z)
• Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design [68.86220939532373]
  The finite precision level is captured through the use of quantized neural networks (QNNs) that quantize weights and activations in fixed-precision format. The proposed FL framework can reduce energy consumption until convergence by up to 70% compared to a baseline FL algorithm.
  arXiv  Detail & Related papers  (2022-07-19T16:37:24Z)
• Neural network enhanced measurement efficiency for molecular groundstates [63.36515347329037]
  We adapt common neural network models to learn complex groundstate wavefunctions for several molecular qubit Hamiltonians. We find that using a neural network model provides a robust improvement over using single-copy measurement outcomes alone to reconstruct observables.
  arXiv  Detail & Related papers  (2022-06-30T17:45:05Z)
• Post-training Quantization for Neural Networks with Provable Guarantees [9.58246628652846]
  We modify a post-training neural-network quantization method, GPFQ, that is based on a greedy path-following mechanism. We prove that for quantizing a single-layer network, the relative square error essentially decays linearly in the number of weights.
  arXiv  Detail & Related papers  (2022-01-26T18:47:38Z)
• Scaling of neural-network quantum states for time evolution [0.0]
  We benchmark the variational power of different shallow and deep neural autoregressive quantum states to simulate global dynamics of a non-integrable quantum Ising chain. We find that the number of parameters required to represent the quantum state at a given accuracy increases exponentially in time.
  arXiv  Detail & Related papers  (2021-04-21T18:00:07Z)
• Gaussian Process States: A data-driven representation of quantum many-body physics [59.7232780552418]
  We present a novel, non-parametric form for compactly representing entangled many-body quantum states. The state is found to be highly compact, systematically improvable and efficient to sample. It is also proven to be a universal approximator' for quantum states, able to capture any entangled many-body state with increasing data set size.
  arXiv  Detail & Related papers  (2020-02-27T15:54:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.