When can classical neural networks represent quantum states?

• URL: http://arxiv.org/abs/2410.23152v1
• Date: Wed, 30 Oct 2024 16:06:53 GMT
• Title: When can classical neural networks represent quantum states?
• Authors: Tai-Hsuan Yang, Mehdi Soleimanifar, Thiago Bergamaschi, John Preskill,
• Abstract summary: A naive classical representation of an n-qubit state requires specifying exponentially many amplitudes in the computational basis. Past works have demonstrated that classical neural networks can succinctly express these amplitudes for many physically relevant states. We show that conditional correlations present in the measurement distribution of quantum states control the performance of their neural representations.
• Score: 0.24749083496491683
• License:
• Abstract: A naive classical representation of an n-qubit state requires specifying exponentially many amplitudes in the computational basis. Past works have demonstrated that classical neural networks can succinctly express these amplitudes for many physically relevant states, leading to computationally powerful representations known as neural quantum states. What underpins the efficacy of such representations? We show that conditional correlations present in the measurement distribution of quantum states control the performance of their neural representations. Such conditional correlations are basis dependent, arise due to measurement-induced entanglement, and reveal features not accessible through conventional few-body correlations often examined in studies of phases of matter. By combining theoretical and numerical analysis, we demonstrate how the state's entanglement and sign structure, along with the choice of measurement basis, give rise to distinct patterns of short- or long-range conditional correlations. Our findings provide a rigorous framework for exploring the expressive power of neural quantum states.

Related papers

• Emergence of global receptive fields capturing multipartite quantum correlations [0.565473932498362]
  In quantum physics, even simple data with a well-defined structure at the wave function level can be characterized by extremely complex correlations. We show that monitoring the neural network weight space while learning quantum statistics allows to develop physical intuition about complex multipartite patterns. Our findings suggest a fresh look at constructing convolutional neural networks for processing data with non-local patterns.
  arXiv  Detail & Related papers  (2024-08-23T12:45:40Z)
• Computational supremacy in quantum simulation [22.596358764113624]
  We show that superconducting quantum annealing processors can generate samples in close agreement with solutions of the Schr"odinger equation. We conclude that no known approach can achieve the same accuracy as the quantum annealer within a reasonable timeframe.
  arXiv  Detail & Related papers  (2024-03-01T19:00:04Z)
• Capturing many-body correlation effects with quantum and classical computing [40.7853309684189]
  We show the efficiency of Quantum Phase Estor (QPE) in identifying core-level states relevant to x-ray photoelectron spectroscopy. We compare and validate the QPE predictions with exact diagonalization and real-time equation-of-motion coupled cluster formulations.
  arXiv  Detail & Related papers  (2024-02-18T01:26:45Z)
• Entanglement transition in deep neural quantum states [0.0]
  We show how information propagation in deep neural networks impacts the physical entanglement properties of deep neural quantum states. With this bridge we can identify optimal neural quantum state hyper parameter regimes for representing area as well as volume law entangled states. This advance of our understanding of network configurations for accurate quantum state representation helps to develop effective representations to deal with volume-law quantum states.
  arXiv  Detail & Related papers  (2023-12-19T08:40:23Z)
• Comment on "Can Neural Quantum States Learn Volume-Law Ground States?" [44.99833362998488]
  We show that suitably chosen NQS can learn ground states with volume-law entanglement both for spin and fermionic problems. We argue that the setup utilized in the aforementioned letter reveals the inefficiency of non-fermionic NQS to learn fermionic states.
  arXiv  Detail & Related papers  (2023-09-20T14:44:04Z)
• Quantum data learning for quantum simulations in high-energy physics [55.41644538483948]
  We explore the applicability of quantum-data learning to practical problems in high-energy physics. We make use of ansatz based on quantum convolutional neural networks and numerically show that it is capable of recognizing quantum phases of ground states. The observation of non-trivial learning properties demonstrated in these benchmarks will motivate further exploration of the quantum-data learning architecture in high-energy physics.
  arXiv  Detail & Related papers  (2023-06-29T18:00:01Z)
• Learning Energy-Based Representations of Quantum Many-Body States [14.781921087738969]
  An ideal representation of a quantum state combines a succinct characterization informed by the system's structure and symmetries, along with the ability to predict the physical observables of interest. Here, we propose a new generative energy-based representation of quantum many-body states derived from Gibbs distributions used for modeling the thermal states of classical spin systems. Our results show that such a representation can be efficiently learned from data using exact algorithms in a form that enables the prediction of expectation values of physical observables.
  arXiv  Detail & Related papers  (2023-04-08T16:01:44Z)
• Can neural quantum states learn volume-law ground states? [0.0]
  We study whether neural quantum states based on multi-layer feed-forward networks can find ground states which exhibit volume-law entanglement entropy. We find that both shallow and deep feed-forward networks require an exponential number of parameters in order to represent the ground state of this model.
  arXiv  Detail & Related papers  (2022-12-05T12:26:20Z)
• Interpretable Quantum Advantage in Neural Sequence Learning [2.575030923243061]
  We study the relative expressive power between a broad class of neural network sequence models and a class of recurrent models based on Gaussian operations with non-Gaussian measurements. We pinpoint quantum contextuality as the source of an unconditional memory separation in the expressivity of the two model classes. In doing so, we demonstrate that our introduced quantum models are able to outperform state of the art classical models even in practice.
  arXiv  Detail & Related papers  (2022-09-28T18:34:04Z)
• 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)
• Entanglement Classification via Neural Network Quantum States [58.720142291102135]
  In this paper we combine machine-learning tools and the theory of quantum entanglement to perform entanglement classification for multipartite qubit systems in pure states. We use a parameterisation of quantum systems using artificial neural networks in a restricted Boltzmann machine (RBM) architecture, known as Neural Network Quantum States (NNS)
  arXiv  Detail & Related papers  (2019-12-31T07:40:23Z)

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.