Out-of-distribution generalization for learning quantum dynamics
CQT Online Talks – Series: Computer Science Seminars
Speaker: Matthias C. Caro, Freie Universität Berlin
Abstract: Generalization bounds are a critical tool to assess the training data requirements of Quantum Machine Learning (QML). Recent work has established guarantees for in-distribution generalization of quantum neural networks (QNNs), where training and testing data are assumed to be drawn from the same data distribution. However, there are currently no results on out-of-distribution generalization in QML, where we require a trained model to perform well even on data drawn from a distribution different from the training distribution. In this talk, we first introduce a mathematical framework for formalizing questions about in-distribution and out-of-distribution generalization. Then, we prove out-of-distribution generalization for the task of learning an unknown unitary using a QNN and for a broad class of training and testing distributions, so-called locally scrambled distributions. In particular, our results show that one can learn the action of a unitary on entangled states using only product state training data. We also discuss some conceptual implications of these out-of-distribution generalization results and illustrate them with two numerical applications.
Based on arXiv:2204.10268.
Watch video Out-of-distribution generalization for learning quantum dynamics online without registration, duration hours minute second in high quality. This video was added by user Centre for Quantum Technologies 17 July 2022, don't forget to share it with your friends and acquaintances, it has been viewed on our site 379 once and liked it 10 people.