Understanding quantum machine learning also requires rethinking generalization

• URL: http://arxiv.org/abs/2306.13461v2
• Date: Mon, 12 Feb 2024 16:30:54 GMT
• Title: Understanding quantum machine learning also requires rethinking generalization
• Authors: Elies Gil-Fuster, Jens Eisert, Carlos Bravo-Prieto
• Abstract summary: We show that traditional approaches to understanding generalization fail to explain the behavior of quantum models. Experiments reveal that state-of-the-art quantum neural networks accurately fit random states and random labeling of training data.
• Score: 0.3683202928838613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum machine learning models have shown successful generalization performance even when trained with few data. In this work, through systematic randomization experiments, we show that traditional approaches to understanding generalization fail to explain the behavior of such quantum models. Our experiments reveal that state-of-the-art quantum neural networks accurately fit random states and random labeling of training data. This ability to memorize random data defies current notions of small generalization error, problematizing approaches that build on complexity measures such as the VC dimension, the Rademacher complexity, and all their uniform relatives. We complement our empirical results with a theoretical construction showing that quantum neural networks can fit arbitrary labels to quantum states, hinting at their memorization ability. Our results do not preclude the possibility of good generalization with few training data but rather rule out any possible guarantees based only on the properties of the model family. These findings expose a fundamental challenge in the conventional understanding of generalization in quantum machine learning and highlight the need for a paradigm shift in the study of quantum models for machine learning tasks.

Related papers

• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• The curse of random quantum data [62.24825255497622]
  We quantify the performances of quantum machine learning in the landscape of quantum data. We find that the training efficiency and generalization capabilities in quantum machine learning will be exponentially suppressed with the increase in qubits. Our findings apply to both the quantum kernel method and the large-width limit of quantum neural networks.
  arXiv  Detail & Related papers  (2024-08-19T12:18:07Z)
• Information-theoretic generalization bounds for learning from quantum data [5.0739329301140845]
  We propose a general mathematical formalism for describing quantum learning by training on classical-quantum data. We prove bounds on the expected generalization error of a quantum learner in terms of classical and quantum information-theoretic quantities. Our work lays a foundation for a unifying quantum information-theoretic perspective on quantum learning.
  arXiv  Detail & Related papers  (2023-11-09T17:21:38Z)
• A General Approach to Dropout in Quantum Neural Networks [1.5771347525430772]
  "Overfitting" is the phenomenon occurring when a given model learns the training data excessively well. With the advent of Quantum Neural Networks as learning models, overfitting might soon become an issue.
  arXiv  Detail & Related papers  (2023-10-06T09:39:30Z)
• Statistical Complexity of Quantum Learning [32.48879688084909]
  This article reviews the complexity of quantum learning using information-theoretic techniques. We focus on data complexity, copy complexity, and model complexity. We highlight the differences between quantum and classical learning by addressing both supervised and unsupervised learning.
  arXiv  Detail & Related papers  (2023-09-20T20:04:05Z)
• ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
  We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows. Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems. We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
  arXiv  Detail & Related papers  (2023-08-22T09:11:53Z)
• 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)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Generalization despite overfitting in quantum machine learning models [0.0]
  We provide a characterization of benign overfitting in quantum models. We show how a class of quantum models exhibits analogous features. We intuitively explain these features according to the ability of the quantum model to interpolate noisy data with locally "spiky" behavior.
  arXiv  Detail & Related papers  (2022-09-12T18:08:45Z)
• Theory of Quantum Generative Learning Models with Maximum Mean Discrepancy [67.02951777522547]
  We study learnability of quantum circuit Born machines (QCBMs) and quantum generative adversarial networks (QGANs) We first analyze the generalization ability of QCBMs and identify their superiorities when the quantum devices can directly access the target distribution. Next, we prove how the generalization error bound of QGANs depends on the employed Ansatz, the number of qudits, and input states.
  arXiv  Detail & Related papers  (2022-05-10T08:05:59Z)
• Out-of-distribution generalization for learning quantum dynamics [2.1503874224655997]
  We show that one can learn the action of a unitary on entangled states having trained only product states. This advances the prospects of learning quantum dynamics on near term quantum hardware.
  arXiv  Detail & Related papers  (2022-04-21T17:15:23Z)

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.