Spectral Truncation Kernels: Noncommutativity in $C^*$-algebraic Kernel Machines
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913726112727040 |
|---|---|
| author | Hashimoto, Yuka Hafid, Ayoub Ikeda, Masahiro Kadri, Hachem |
| author_facet | Hashimoto, Yuka Hafid, Ayoub Ikeda, Masahiro Kadri, Hachem |
| contents | $C^*$-algebra-valued kernels could pave the way for the next generation of kernel machines. To further our fundamental understanding of learning with $C^*$-algebraic kernels, we propose a new class of positive definite kernels based on the spectral truncation. We focus on kernels whose inputs and outputs are vectors or functions and generalize typical kernels by introducing the noncommutativity of the products appearing in the kernels. The noncommutativity induces interactions along the data function domain. We show that the proposed kernels fill the gap between existing separable and commutative kernels. We also propose a deep learning perspective to obtain a more flexible framework. The flexibility of the proposed class of kernels allows us to go beyond previous separable and commutative kernels, addressing two of the foremost issues regarding learning in vector-valued RKHSs, namely the choice of the kernel and the computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17823 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Spectral Truncation Kernels: Noncommutativity in $C^*$-algebraic Kernel Machines Hashimoto, Yuka Hafid, Ayoub Ikeda, Masahiro Kadri, Hachem Machine Learning Operator Algebras $C^*$-algebra-valued kernels could pave the way for the next generation of kernel machines. To further our fundamental understanding of learning with $C^*$-algebraic kernels, we propose a new class of positive definite kernels based on the spectral truncation. We focus on kernels whose inputs and outputs are vectors or functions and generalize typical kernels by introducing the noncommutativity of the products appearing in the kernels. The noncommutativity induces interactions along the data function domain. We show that the proposed kernels fill the gap between existing separable and commutative kernels. We also propose a deep learning perspective to obtain a more flexible framework. The flexibility of the proposed class of kernels allows us to go beyond previous separable and commutative kernels, addressing two of the foremost issues regarding learning in vector-valued RKHSs, namely the choice of the kernel and the computational cost. |
| title | Spectral Truncation Kernels: Noncommutativity in $C^*$-algebraic Kernel Machines |
| topic | Machine Learning Operator Algebras |
| url | https://arxiv.org/abs/2405.17823 |