QRC Seminar Series: Prof. Dr. Keisuke Fujii

Mar 18, 2024
QRC Seminar Banner

Prof. Dr. Keisuke Fujii

Professor, Graduate School of Engineering Science, Osaka University

Deputy Director, Center for Quantum Information and Quantum Biology, Osaka University

Team Leader, Quantum Computing Theory Research Team, RIKEN Center for Quantum Computing


18th March 2024 - 5:00pm - 6:00pm (GST)

Title:Quantum Machine Learning: interplay between implicit and explicit quantum models
Abstract:Quantum machine learning is a promising field for quantum computers and various models have been explored. These models can be broadly categorized as either implicit models that leverage quantum kernel methods or explicit models, known as quantum circuit learning. Implicit models consistently achieve lower training errors than explicit models but face linear prediction time scaling with the training data size. In contrast, explicit models predict in constant time. Additionally, implicit models tend to overfit training datasets, which may result in weaker generalization compared to explicit models under certain conditions. However, explicit models' optimization faces inherent challenges due to the barren plateau phenomenon. In this study, we introduce a quantum-classical hybrid algorithm designed to systematically and efficiently convert an implicit model to an explicit model. This explicit model exhibits as high performance as the implicit model and can perform inference with a much smaller number of quantum circuit executions. In classification tasks using both MNISQ and VQE-generated datasets, we demonstrate that the explicit model we developed offers a generalization comparable to that of the implicit model but with reduced computational costs. These results suggest that our proposed algorithm not only reduces the prediction time of implicit models but also aids in constructing high-performance explicit models, especially in addressing challenges such as the barren plateau phenomenon. In addition, our activities on the development of infrastructure for developing quantum machine learning, quantum datasets, libraries, simulators, etc. will be presented.
Bio:Keisuke Fujii is a leading expert in theory and software research of quantum computer including near-term applications of quantum computer and fault-tolerant quantum computing. He obtained Ph.D. in Engineering at Kyoto University (2011). Since 2019, he has served as Professor at Graduate School of Engineering Science in Osaka University, Deputy Director of Center for Quantum Information and Quantum Biology in Osaka University (2020-), and Team Leader of RIKEN Center for Quantum Computing (2021-). In addition, served as R&D Project Leader of Quantum Software Research Hub (JST COI NEXT), Project Leader of Quantum Leap Flagship Program (MEXT Q-LEAP), and Principal Investigator of Moonshot Research and Development Program (JST). He received Kyoto University President Prize (2011), Osaka University Award(2020), NISTEP Award(2020), JSPS Prize(2022), and Osaka University Distinguished Professor(2022). His areas of expertise include theoretical and software research on quantum computers.