Theory of overparametrization in quantum neural networks
CQT Online Talks - Series: Quantum Machine Learning Journal Club Talks
Speakers: Martin Larocca, Universidad de Buenos Aires, Los Alamos National Laboratory
Abstract: The prospect of achieving quantum advantage with Quantum Neural Networks (QNNs) is exciting. Understanding how QNN properties (e.g., the number of parameters M) affect the loss landscape is crucial to the design of scalable QNN architectures. Here, we rigorously analyze the overparametrization phenomenon in QNNs with periodic structure. We define overparametrization as the regime where the QNN has more than a critical number of parameters Mc that allows it to explore all relevant directions in state space. Our main results show that the dimension of the Lie algebra obtained from the generators of the QNN is an upper bound for Mc, and for the maximal rank that the quantum Fisher information and Hessian matrices can reach. Underparametrized QNNs have spurious local minima in the loss landscape that start disappearing when M﹥Mc. Thus, the overparametrization onset corresponds to a computational phase transition where the QNN trainability is greatly improved by a more favorable landscape. We then connect the notion of overparametrization to the QNN capacity, so that when a QNN is overparametrized, its capacity achieves its maximum possible value. We run numerical simulations for eigensolver, compilation, and autoencoding applications to showcase the overparametrization computational phase transition. We note that our results also apply to variational quantum algorithms and quantum optimal control.
Watch video Theory of overparametrization in quantum neural networks online without registration, duration hours minute second in high quality. This video was added by user Centre for Quantum Technologies 15 November 2021, don't forget to share it with your friends and acquaintances, it has been viewed on our site 738 once and liked it 29 people.