Statistical Limits of Supervised Quantum Learning
This work addresses the fundamental limits of quantum speedups in supervised learning for researchers in quantum computing and machine learning, showing incremental constraints on quantum advantages.
The paper demonstrates that quantum machine learning algorithms for supervised learning cannot achieve polylogarithmic runtimes in input dimension when statistical accuracy bounds are considered, limiting them to at most polynomial speedups over classical algorithms.
Within the framework of statistical learning theory it is possible to bound the minimum number of samples required by a learner to reach a target accuracy. We show that if the bound on the accuracy is taken into account, quantum machine learning algorithms for supervised learning---for which statistical guarantees are available---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 polynomial speedups over efficient classical algorithms, even in cases where quantum access to the data is naturally available.