Quantifying scrambling in quantum neural networks

A bstract We quantify the role of scrambling in quantum machine learning. characterize a neural network’s (QNNs) error terms properties via out-of-time-ordered correlator (OTOC). network can be trained by minimizing loss function. show that function bounded OTOC. prove gradient This demonstrates OTOC landscape regulates trainability QNN. numerically this is flat for maximally QNNs, which pose challenge to training. Our results pave way exploration chaos networks.