Shadows of quantum machine learning

The conceptual idea of generating shadows of quantum models was already proposed by Schreiber et al. [18], albeit under the terminology of classical surrogates. In that Quantum machine learning is a rapidly growing field [1-3] work, as well as in that of Landman et al. [19], the authors driven by its potential to achieve quantum advantages make use of the general expression of quantum models as in practical applications. A particularly interesting approach trigonometric polynomials [20] to learn the Fourier representation to make quantum machine learning applicable of trained models and evaluate them classically in the near term is to develop learning models based on new data. However, these works also suggest that a on parametrized quantum circuits [4-6]. Indeed, such classical model could potentially be trained directly on quantum models have already been shown to achieve the training data and achieve the same performance as good learning performance in benchmarking tasks, both the shadow model, thus circumventing the need for a in numerical simulations [7-11] and on actual quantum quantum model in the first place. This raises the concern hardware [12-15]. Moreover, based on widely-believed that all quantum models that are compatible with a classical cryptography assumptions, these models also hold the deployment would also lose all quantum advantage, promise to solve certain learning tasks that are intractable hence severely limiting the prospects for a widespread use for classical algorithms [16, 17]. of quantum machine learning. Despite these advances, quantum machine learning is Therefore, two natural open questions are raised: facing a major obstacle for its use in practice. A typical workflow of a machine learning model involved, e.g., 1. Can shadow models achieve a quantum advantage in driving autonomous vehicles, is divided into: (i) a over entirely classical (classically trained and classically training phase, where the model is trained, typically using evaluated) models?