Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks

• URL: http://arxiv.org/abs/2307.16083v2
• Date: Mon, 30 Oct 2023 15:55:43 GMT
• Title: Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks
• Authors: Fangjun Hu, Gerasimos Angelatos, Saeed A. Khan, Marti Vives, Esin T\"ureci, Leon Bello, Graham E. Rowlands, Guilhem J. Ribeill, Hakan E. T\"ureci
• Abstract summary: We present a framework for evaluating the resolvable expressive capacity (REC) of general physical systems under finite sampling noise. We then provide empirical evidence that extracting low-noise eigentasks can lead to improved performance for machine learning tasks. Our findings have broad implications for quantum machine learning and sensing applications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The expressive capacity of physical systems employed for learning is limited by the unavoidable presence of noise in their extracted outputs. Though present in physical systems across both the classical and quantum regimes, the precise impact of noise on learning remains poorly understood. Focusing on supervised learning, we present a mathematical framework for evaluating the resolvable expressive capacity (REC) of general physical systems under finite sampling noise, and provide a methodology for extracting its extrema, the eigentasks. Eigentasks are a native set of functions that a given physical system can approximate with minimal error. We show that the REC of a quantum system is limited by the fundamental theory of quantum measurement, and obtain a tight upper bound for the REC of any finitely-sampled physical system. We then provide empirical evidence that extracting low-noise eigentasks can lead to improved performance for machine learning tasks such as classification, displaying robustness to overfitting. We present analyses suggesting that correlations in the measured quantum system enhance learning capacity by reducing noise in eigentasks. The applicability of these results in practice is demonstrated with experiments on superconducting quantum processors. Our findings have broad implications for quantum machine learning and sensing applications.

Related papers

• Disentanglement process in dephasing channel with machine learning [0.0]
  We employ a machine-learning approach to investigate the disentanglement process in two-qubit systems in the presence of dephasing noise. Specialized ANN algorithms, tailored for classifying states and entanglement, demonstrate excellent performance using only a subset of tomographic features.
  arXiv  Detail & Related papers  (2024-10-28T20:18:04Z)
• Generalization Error in Quantum Machine Learning in the Presence of Sampling Noise [0.8532753451809455]
  Eigentask Learning is a framework for learning with infinite input training data in the presence of output sampling noise. We calculate the training and generalization errors of a generic quantum machine learning system when the input training dataset and output measurement sampling shots are both finite.
  arXiv  Detail & Related papers  (2024-10-18T17:48:24Z)
• Noise-assisted digital quantum simulation of open systems [1.3124513975412255]
  We present a novel approach that capitalizes on the intrinsic noise of quantum devices to reduce the computational resources required for simulating open quantum systems. Specifically, we selectively enhance or reduce decoherence rates in the quantum circuit to achieve the desired simulation of open system dynamics.
  arXiv  Detail & Related papers  (2023-02-28T14:21:43Z)
• Quantifying the Expressive Capacity of Quantum Systems: Fundamental Limits and Eigentasks [0.0]
  expressive capacity of quantum systems for machine learning is limited by quantum sampling noise incurred during measurement. We present a mathematical framework for evaluating the available expressive capacity of general quantum systems from a finite number of measurements. We show that extracting low-noise eigentasks leads to improved performance for machine learning tasks such as classification, displaying robustness to overfitting.
  arXiv  Detail & Related papers  (2022-12-30T20:15:31Z)
• Potential and limitations of quantum extreme learning machines [55.41644538483948]
  We present a framework to model QRCs and QELMs, showing that they can be concisely described via single effective measurements. Our analysis paves the way to a more thorough understanding of the capabilities and limitations of both QELMs and QRCs.
  arXiv  Detail & Related papers  (2022-10-03T09:32:28Z)
• Noisy Quantum Kernel Machines [58.09028887465797]
  An emerging class of quantum learning machines is that based on the paradigm of quantum kernels. We study how dissipation and decoherence affect their performance. We show that decoherence and dissipation can be seen as an implicit regularization for the quantum kernel machines.
  arXiv  Detail & Related papers  (2022-04-26T09:52:02Z)
• Quantum-tailored machine-learning characterization of a superconducting qubit [50.591267188664666]
  We develop an approach to characterize the dynamics of a quantum device and learn device parameters. This approach outperforms physics-agnostic recurrent neural networks trained on numerically generated and experimental data. This demonstration shows how leveraging domain knowledge improves the accuracy and efficiency of this characterization task.
  arXiv  Detail & Related papers  (2021-06-24T15:58:57Z)
• Quantum circuit architecture search for variational quantum algorithms [88.71725630554758]
  We propose a resource and runtime efficient scheme termed quantum architecture search (QAS) QAS automatically seeks a near-optimal ansatz to balance benefits and side-effects brought by adding more noisy quantum gates. We implement QAS on both the numerical simulator and real quantum hardware, via the IBM cloud, to accomplish data classification and quantum chemistry tasks.
  arXiv  Detail & Related papers  (2020-10-20T12:06:27Z)
• Quantum Non-equilibrium Many-Body Spin-Photon Systems [91.3755431537592]
  dissertation concerns the quantum dynamics of strongly-correlated quantum systems in out-of-equilibrium states. Our main results can be summarized in three parts: Signature of Critical Dynamics, Driven Dicke Model as a Test-bed of Ultra-Strong Coupling, and Beyond the Kibble-Zurek Mechanism.
  arXiv  Detail & Related papers  (2020-07-23T19:05:56Z)
• Beyond Quantum Noise Spectroscopy: modelling and mitigating noise with quantum feature engineering [0.0]
  The ability to use quantum technology to achieve useful tasks, be they scientific or industry related, boils down to precise quantum control. In general it is difficult to assess a proposed solution due to the difficulties in characterising the quantum system or device. Here we present a general purpose characterisation and control solution making use of a novel deep learning framework composed of quantum features.
  arXiv  Detail & Related papers  (2020-03-15T13:24:45Z)
• Machine learning transfer efficiencies for noisy quantum walks [62.997667081978825]
  We show that the process of finding requirements on both a graph type and a quantum system coherence can be automated. The automation is done by using a convolutional neural network of a particular type that learns to understand with which network and under which coherence requirements quantum advantage is possible. Our results are of importance for demonstration of advantage in quantum experiments and pave the way towards automating scientific research and discoveries.
  arXiv  Detail & Related papers  (2020-01-15T18:36:53Z)

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.