Quantum tangent kernel

• Item type: SIG Technical Reports(1)
• 公開日: 2022-06-30
• タイトル: Quantum tangent kernel
• タイトル / 言語: en
• タイトル: Quantum tangent kernel
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Graduate School of Engineering Science, Osaka University
• 著者所属: Graduate School of Engineering Science, Osaka University／R4D, Mercari Inc.
• 著者所属: Graduate School of Engineering Science, Osaka University／Center for Quantum Information and Quantum Biology, Osaka University／JST, PRESTO
• 著者所属: Graduate School of Engineering Science, Osaka University／Center for Quantum Information and Quantum Biology, Osaka University／RIKEN Center for Quantum Computing
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering Science, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering Science, Osaka University / R4D, Mercari Inc.
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering Science, Osaka University / Center for Quantum Information and Quantum Biology, Osaka University / JST, PRESTO
• 著者所属(英): en
• 著者所属(英): Graduate School of Engineering Science, Osaka University / Center for Quantum Information and Quantum Biology, Osaka University / RIKEN Center for Quantum Computing
• 著者名: Norihito, Shirai; Kenji, Kubo; Kosuke, Mitarai; Keisuke, Fujii
• 著者名(英): Norihito, Shirai; Kenji, Kubo; Kosuke, Mitarai; Keisuke, Fujii
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Quantum kernel method is one of the key approaches to quantum machine learning, which has the advantages that it does not require optimization and has theoretical simplicity. By virtue of these properties, several experimental demonstrations and discussions of the potential advantages have been developed so far. However, as is the case in classical machine learning, not all quantum machine learning models could be regarded as kernel methods. In this work, we explore a quantum machine learning model with a deep parameterized quantum circuit and aim to go beyond the conventional quantum kernel method. In this case, the representation power and performance are expected to be enhanced, while the training process might be a bottleneck because of the barren plateaus issue. However, we find that parameters of a deep enough quantum circuit do not move much from its initial values during training, allowing first-order expansion with respect to the parameters. This behavior is similar to the neural tangent kernel in the classical literatures, and such a deep variational quantum machine learning can be described by another emergent kernel, quantum tangent kernel. Numerical simulations show that the proposed quantum tangent kernel outperforms the conventional quantum kernel method for an ansatz-generated dataset. This work provides a new direction beyond the conventional quantum kernel method and explores potential power of quantum machine learning with deep parameterized quantum circuits.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Quantum kernel method is one of the key approaches to quantum machine learning, which has the advantages that it does not require optimization and has theoretical simplicity. By virtue of these properties, several experimental demonstrations and discussions of the potential advantages have been developed so far. However, as is the case in classical machine learning, not all quantum machine learning models could be regarded as kernel methods. In this work, we explore a quantum machine learning model with a deep parameterized quantum circuit and aim to go beyond the conventional quantum kernel method. In this case, the representation power and performance are expected to be enhanced, while the training process might be a bottleneck because of the barren plateaus issue. However, we find that parameters of a deep enough quantum circuit do not move much from its initial values during training, allowing first-order expansion with respect to the parameters. This behavior is similar to the neural tangent kernel in the classical literatures, and such a deep variational quantum machine learning can be described by another emergent kernel, quantum tangent kernel. Numerical simulations show that the proposed quantum tangent kernel outperforms the conventional quantum kernel method for an ansatz-generated dataset. This work provides a new direction beyond the conventional quantum kernel method and explores potential power of quantum machine learning with deep parameterized quantum circuits.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA12894105
• 書誌情報: 量子ソフトウェア（QS）; 巻 2022-QS-6, 号 4, p. 1-6, 発行日 2022-06-30
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2435-6492
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会