Quantum Learning Boolean Linear Functions w.r.t. Product Distributions
This work addresses the challenge of extending quantum learning beyond uniform distributions, offering incremental improvements in sample efficiency for specific bias conditions in quantum machine learning.
The paper tackles the problem of learning Boolean linear functions from quantum examples under biased product distributions, developing two quantum algorithms: one requiring O(ln(n)) examples for any bias except full, and another with sample complexity independent of n for small bias, while also proving lower bounds showing classical requires Ω(n) examples and quantum requires Ω(ln(n)) under large bias.
The problem of learning Boolean linear functions from quantum examples w.r.t. the uniform distribution can be solved on a quantum computer using the Bernstein-Vazirani algorithm. A similar strategy can be applied in the case of noisy quantum training data, as was observed in arXiv:1702.08255v2 [quant-ph]. However, extensions of these learning algorithms beyond the uniform distribution have not yet been studied. We employ the biased quantum Fourier transform introduced in arXiv:1802.05690v2 [quant-ph] to develop efficient quantum algorithms for learning Boolean linear functions on $n$ bits from quantum examples w.r.t. a biased product distribution. Our first procedure is applicable to any (except full) bias and requires $\mathcal{O}(\ln (n))$ quantum examples. The number of quantum examples used by our second algorithm is independent of $n$, but the strategy is applicable only for small bias. Moreover, we show that the second procedure is stable w.r.t. noisy training data and w.r.t. faulty quantum gates. This also enables us to solve a version of the learning problem in which the underlying distribution is not known in advance. Finally, we prove lower bounds on the classical and quantum sample complexities of the learning problem. Whereas classically, $Ω(n)$ examples are necessary independently of the bias, we are able to establish a quantum sample complexity lower bound of $Ω(\ln (n))$ only under an assumption of large bias. Nevertheless, this allows for a discussion of the performance of our suggested learning algorithms w.r.t. sample complexity. With our analysis we contribute to a more quantitative understanding of the power and limitations of quantum training data for learning classical functions.