Highly entangled and highly non-stabilizer quantum states need not be hard to learn. We give efficient algorithms for testing and recovering hidden tensor-product structure in unknown pure state vectors of the form $\lvert\psi\rangle = U_C \bigotimes_i \lvert\psi_i\rangle$, where $U_C$ is an arbitrary unknown Clifford...
G. Aguilar, Sofiène Jerbi, J. Eisert et al.· 1 citation
This work studies the simplified setting of reinforcement learning with a uniform generative model in which uniformly random state-action samples are available, and provides finite sample guarantees for classical kernelized Fitted Q-Iteration, with classical kernels designed to match the inductive bias of particular pa...
Pablo Rodriguez-Grasa, Sofiène Jerbi, Mikel Sanz et al.· 0 citations
The results demonstrate a rigorous learning separation for a natural ML task based on Hamiltonian evolution, while building connections between quantum learning theory, quantum simulation, and QML.