Generalization Error in Quantum Machine Learning in the Presence of Sampling Noise

• URL: http://arxiv.org/abs/2410.14654v2
• Date: Mon, 28 Oct 2024 18:32:29 GMT
• Title: Generalization Error in Quantum Machine Learning in the Presence of Sampling Noise
• Authors: Fangjun Hu, Xun Gao,
• Abstract summary: 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.
• Score: 0.8532753451809455
• License:
• Abstract: Tackling output sampling noise due to finite shots of quantum measurement is an unavoidable challenge when extracting information in machine learning with physical systems. A technique called Eigentask Learning was developed recently as a framework for learning with infinite input training data in the presence of output sampling noise. In the work of Eigentask Learning, numerical evidence was presented that extracting low-noise contributions of features can practically improve performance for machine learning tasks, displaying robustness to overfitting and increasing generalization accuracy. However, it remains unsolved to quantitatively characterize generalization errors in situations where the training dataset is finite, while output sampling noise still exists. In this study, we use methodologies from statistical mechanics to 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. Our analytical findings, supported by numerical validation, offer solid justification that Eigentask Learning provides optimal learning in the sense of minimizing generalization errors.

Related papers

• Learning Density Functionals from Noisy Quantum Data [0.0]
  noisy intermediate-scale quantum (NISQ) devices are used to generate training data for machine learning (ML) models. We show that a neural-network ML model can successfully generalize from small datasets subject to noise typical of NISQ algorithms. Our findings suggest a promising pathway for leveraging NISQ devices in practical quantum simulations.
  arXiv  Detail & Related papers  (2024-09-04T17:59:55Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• Tackling Sampling Noise in Physical Systems for Machine Learning Applications: Fundamental Limits and Eigentasks [0.0]
  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.
  arXiv  Detail & Related papers  (2023-07-29T21:39:29Z)
• Transition Role of Entangled Data in Quantum Machine Learning [51.6526011493678]
  Entanglement serves as the resource to empower quantum computing. Recent progress has highlighted its positive impact on learning quantum dynamics. We establish a quantum no-free-lunch (NFL) theorem for learning quantum dynamics using entangled data.
  arXiv  Detail & Related papers  (2023-06-06T08:06:43Z)
• Deep Active Learning with Noise Stability [24.54974925491753]
  Uncertainty estimation for unlabeled data is crucial to active learning. We propose a novel algorithm that leverages noise stability to estimate data uncertainty. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis.
  arXiv  Detail & Related papers  (2022-05-26T13:21:01Z)
• Overfitting in quantum machine learning and entangling dropout [0.9404723842159504]
  The ultimate goal in machine learning is to construct a model function that has a generalization capability for unseen dataset. If the model function has too much expressibility power, then it may overfit to the training data and as a result lose the generalization capability. This paper proposes a straightforward analogue of this technique in the quantum machine learning regime, the entangling dropout.
  arXiv  Detail & Related papers  (2022-05-23T16:35:46Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)
• Learnability of Learning Performance and Its Application to Data Valuation [11.78594243870616]
  In most machine learning (ML) tasks, evaluating learning performance on a given dataset requires intensive computation. The ability to efficiently estimate learning performance may benefit a wide spectrum of applications, such as active learning, data quality management, and data valuation. Recent empirical studies show that for many common ML models, one can accurately learn a parametric model that predicts learning performance for any given input datasets using a small amount of samples.
  arXiv  Detail & Related papers  (2021-07-13T18:56:04Z)
• 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)
• Automatic Recall Machines: Internal Replay, Continual Learning and the Brain [104.38824285741248]
  Replay in neural networks involves training on sequential data with memorized samples, which counteracts forgetting of previous behavior caused by non-stationarity. We present a method where these auxiliary samples are generated on the fly, given only the model that is being trained for the assessed objective. Instead the implicit memory of learned samples within the assessed model itself is exploited.
  arXiv  Detail & Related papers  (2020-06-22T15:07:06Z)
• Statistical Limits of Supervised Quantum Learning [90.0289160657379]
  We show that if the bound on the accuracy is taken into account, quantum machine learning algorithms for supervised learning cannot achieve polylogarithmic runtimes in the input dimension. We conclude that, when no further assumptions on the problem are made, quantum machine learning algorithms for supervised learning can have at most speedups over efficient classical algorithms.
  arXiv  Detail & Related papers  (2020-01-28T17:35:32Z)

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.