Training Quantum Neural Networks Using Meta Optimization

According to an aspect of an embodiment, operations include receiving a dataset associated with a machine learning task, preparing an input quantum state based on the dataset, and preparing a VQC to function as a QNN. The operations further include executing operations comprising reading content of a state buffer as empty or including past information on parameters of the QNN, selecting parameter values based on the content, preparing an input for an optimizer network based on the parameter values, computing an output by applying the optimizer network on the input, updating the parameter values using the output, and obtaining a current cost function value based on the updated parameter values. The operations further include updating the state buffer using the current cost function value and the updated parameters values and training the QNN until the current cost function value is below a threshold.