Trainability of IQP Quantum Circuit Born Machines Under Gaussian Initialization
Researchers have analyzed the trainability of Quantum Circuit Born Machines (QCBMs) that utilize Instantaneous Quantum Polynomial (IQP) circuits, specifically under Gaussian initialization schemes. The study employs Stein's lemma and Lipschitz concentration bounds to establish analytical lower bounds for gradient variance and probabilistic concentration bounds for gradient deviation. This work aims to identify conditions that lead to barren plateaus and offers strategies to either avoid or encourage exponential concentration in these quantum machine learning models. AI