On measurement-dependent variance in quantum neural networks

• URL: http://arxiv.org/abs/2601.08029v1
• Date: Mon, 12 Jan 2026 22:01:32 GMT
• Title: On measurement-dependent variance in quantum neural networks
• Authors: Andrey Kardashin, Konstantin Antipin,
• Abstract summary: We show that measuring observables with restricted support results in larger label prediction variance in regression QML tasks.<n>We show that the reason for this is, essentially, the number of distinct eigenvalues of the observable one measures after the application of a variational circuit.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational quantum circuits have become a widely used tool for performing quantum machine learning (QML) tasks on labeled quantum states. In some specific tasks or for specific variational ansätze, one may perform measurements on a restricted part of the overall input state. This is the case for, e.g., quantum convolutional neural networks (QCNNs), where after each layer of the circuit a subset of qubits of the processed state is measured or traced out, and at the end of the network one typically measures a local observable. In this work, we demonstrate that measuring observables with restricted support results in larger label prediction variance in regression QML tasks. We show that the reason for this is, essentially, the number of distinct eigenvalues of the observable one measures after the application of a variational circuit.

Related papers

• Measuring Incompatible Observables with Quantum Neural Networks [0.641460223525021]
  Heisenberg uncertainty principle prevents simultaneous measurements of incompatible observables.<n>We show that by implementing a multiple-output QNN that emulates a unital quantum channel, one can measure the expectation values of many incompatible observables simultaneously.
  arXiv  Detail & Related papers  (2025-03-26T14:03:42Z)
• Benchmarking Variational Quantum Eigensolvers for Entanglement Detection in Many-Body Hamiltonian Ground States [37.69303106863453]
  Variational quantum algorithms (VQAs) have emerged in recent years as a promise to obtain quantum advantage. We use a specific class of VQA named variational quantum eigensolvers (VQEs) to benchmark them at entanglement witnessing and entangled ground state detection. Quantum circuits whose structure is inspired by the Hamiltonian interactions presented better results on cost function estimation than problem-agnostic circuits.
  arXiv  Detail & Related papers  (2024-07-05T12:06:40Z)
• Certifying almost all quantum states with few single-qubit measurements [0.9558392439655012]
  We show that almost all n-qubit target states can be certified from only O(n2) single-qubit measurements. We show that such verified representations can be used to efficiently predict highly non-local properties.
  arXiv  Detail & Related papers  (2024-04-10T18:21:11Z)
• What can we learn from quantum convolutional neural networks? [15.236546465767026]
  We show how models utilizing quantum data can be interpreted through hidden feature maps.<n>High performance in quantum phase recognition comes from generating a highly effective basis set with sharp features at critical points.<n>Our analysis highlights improved generalization when working with quantum data.
  arXiv  Detail & Related papers  (2023-08-31T12:12:56Z)
• Quantum Process Learning Through Neural Emulation [3.7228085662092845]
  We introduce a neural network that emulates the unknown process by constructing an internal representation of the input ensemble. We show that our model exhibits high accuracy in applications to quantum computing, quantum photonics, and quantum many-body physics.
  arXiv  Detail & Related papers  (2023-08-17T06:53:58Z)
• Randomness-enhanced expressivity of quantum neural networks [7.7991930692137466]
  We propose a novel approach to enhance the expressivity of QNNs by incorporating randomness into quantum circuits. We prove that our approach can accurately approximate arbitrary target operators using Uhlmann's theorem for majorization. We find the expressivity of QNNs is enhanced by introducing randomness for multiple learning tasks, which could have broad application in quantum machine learning.
  arXiv  Detail & Related papers  (2023-08-09T07:17:13Z)
• Applicability of Measurement-based Quantum Computation towards Physically-driven Variational Quantum Eigensolver [17.975555487972166]
  Variational quantum algorithms are considered one of the most promising methods for obtaining near-term quantum advantages. The roadblock to developing quantum algorithms with the measurement-based quantum computation scheme is resource cost. We propose an efficient measurement-based quantum algorithm for quantum many-body system simulation tasks, called measurement-based Hamiltonian variational ansatz (MBHVA)
  arXiv  Detail & Related papers  (2023-07-19T08:07:53Z)
• Quantum State Tomography for Matrix Product Density Operators [28.799576051288888]
  Reconstruction of quantum states from experimental measurements is crucial for the verification and benchmarking of quantum devices. Many physical quantum states, such as states generated by noisy, intermediate-scale quantum computers, are usually structured. We establish theoretical guarantees for the stable recovery of MPOs using tools from compressive sensing and the theory of empirical processes.
  arXiv  Detail & Related papers  (2023-06-15T18:23:55Z)
• 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)
• Quantum algorithms for grid-based variational time evolution [36.136619420474766]
  We propose a variational quantum algorithm for performing quantum dynamics in first quantization. Our simulations exhibit the previously observed numerical instabilities of variational time propagation approaches.
  arXiv  Detail & Related papers  (2022-03-04T19:00:45Z)
• Methods for measuring noise, purity changes, and entanglement entropy in quantum devices and systems [0.0]
  We present methods for evaluating the rate of change in quantities during quantum evolution due to coupling to the environment. We start by applying this method for measuring the rate of purity changes in quantum circuits. The presented scheme enables to distill the dissipative contribution in the changes of quantities such as energies and coherence.
  arXiv  Detail & Related papers  (2021-12-01T15:07:29Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• Genuine quantum networks: superposed tasks and addressing [68.8204255655161]
  We show how to make quantum networks, both standard and entanglement-based, genuine quantum. We provide them with the possibility of handling superposed tasks and superposed addressing.
  arXiv  Detail & Related papers  (2020-04-30T18:00:06Z)

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.