BEINIT: Avoiding Barren Plateaus in Variational Quantum Algorithms
This addresses a critical obstacle for researchers developing more efficient quantum machine learning algorithms, though it appears incremental as it builds on existing initialization strategies.
The paper tackles the problem of barren plateaus in variational quantum algorithms by proposing a data-driven initialization using beta distributions and gradient perturbations, empirically showing a significant reduction in the likelihood of getting stuck.
Barren plateaus are a notorious problem in the optimization of variational quantum algorithms and pose a critical obstacle in the quest for more efficient quantum machine learning algorithms. Many potential reasons for barren plateaus have been identified but few solutions have been proposed to avoid them in practice. Existing solutions are mainly focused on the initialization of unitary gate parameters without taking into account the changes induced by input data. In this paper, we propose an alternative strategy which initializes the parameters of a unitary gate by drawing from a beta distribution. The hyperparameters of the beta distribution are estimated from the data. To further prevent barren plateau during training we add a novel perturbation at every gradient descent step. Taking these ideas together, we empirically show that our proposed framework significantly reduces the possibility of a complex quantum neural network getting stuck in a barren plateau.