… exists between efficient quantum learnability and efficient clasical learnability. Undcr a widely
held … -time learnable in the quantum version but not in the classical version of the model. …

… learning algorithm must have a polynomial-time classical … quantum learnability and efficient
classical learnability. Under a widely held computational hardness assumption for classical …

… Here we study the comparative power of classical and quantum learners for … learnable
by a classical generative modelling algorithm, but for which we construct an efficient quantum …

… Intuitively, this result means that anything we can do with quantum advice, we can also do
with classical advice, provided we are willing to use exponentially more computation time to …

… of the underlying probability distribution, and evaluate the corresponding learnability of
the associated samples. We perform such test with both quantum and classical samples. For …

… Our work provides theoretical guidance for developing advanced QNNs and opens up
avenues for exploring quantum advantages beyond hybrid quantum-classical learning protocols …

… This theorem shows that every set of quantum states C is PAC learnable with respect to
measurements M (distributed according to D) with only a linear in n number of data points. To …

… In this paper, we mainly test the learnability of a hybrid quantum-classical neural network
for graph-structured quantum data. The model and training algorithm of this process are …

… We say that a concept class C is polynomial-time learnable from quantum membership …
we construct in Section 5 is learnable in poly(n) time by a quantum algorithm. Recall that in our …

… provable separation between classical and quantum learnability. This implies that hard
classical problems might benefit significantly from the adoption of quantum-based computational …