Learning in RKHM: a $C^*$-Algebraic Twist for Kernel Machines

2022-10-21 · Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri

Supervised learning in reproducing kernel Hilbert space (RKHS) and vector-valued RKHS (vvRKHS) has been investigated for more than 30 years. In this paper, we provide a new twist to this rich literature by generalizing supervised learning in RKHS and vvRKHS to reproducing kernel Hilbert $C^*$-module (RKHM), and show how to construct effective positive-definite kernels by considering the perspective of $C^*$-algebra. Unlike the cases of RKHS and vvRKHS, we can use $C^*$-algebras to enlarge representation spaces. This enables us to construct RKHMs whose representation power goes beyond RKHSs, vvRKHSs, and existing methods such as convolutional neural networks. Our framework is suitable, for example, for effectively analyzing image data by allowing the interaction of Fourier components.

📄 PDF Abstract BibTeX arXiv:2210.11855

Code (0)

등록된 구현이 없습니다.

Reproducing kernel Hilbert C*-module and kernel mean embeddings

2021-01-27 · Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura 외

Kernel methods have been among the most popular techniques in machine learning, where learning tasks are solved using the property of reproducing kernel Hilbert space (RKHS). In this paper, we propose a novel data analys…

Analysis via Orthonormal Systems in Reproducing Kernel Hilbert $C^*$-Modules and Applications

2020-03-02 · Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura 외

Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator

2023-05-23 · NeurIPS 2023 11

Reproducing kernel Hilbert $C^*$-module (RKHM) is a generalization of reproducing kernel Hilbert space (RKHS) by means of $C^*$-algebra, and the Perron-Frobenius operator is a linear operator related to the composition o…

Deep Learning

Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams

2018-02-10 · NeurIPS 2018 12 · Tam Le, Makoto Yamada

Algebraic topology methods have recently played an important role for statistical analysis with complicated geometric structured data such as shapes, linked twist maps, and material data. Among them, \textit{persistent h…

Kernel Mean Embeddings of Von Neumann-Algebra-Valued Measures

2020-07-29 · Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura 외

Kernel mean embedding (KME) is a powerful tool to analyze probability measures for data, where the measures are conventionally embedded into a reproducing kernel Hilbert space (RKHS). In this paper, we generalize KME to …