Entangled Kernels

Abstract : We consider the problem of operator-valued kernel learning and investigate the possibility of going beyond the well-known separable kernels. Borrowing tools and concepts from the field of quantum computing , such as partial trace and entanglement, we propose a new view on operator-valued kernels and define a general family of kernels that encompasses previously known operator-valued kernels, including separable and transformable kernels. Within this framework, we introduce another novel class of operator-valued kernels called entangled kernels that are not separable. We propose an efficient two-step algorithm for this framework, where the entangled kernel is learned based on a novel extension of kernel alignment to operator-valued kernels. The utility of the algorithm is illustrated on both artificial and real data.
Document type :
Conference papers
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02187162
Contributor : Riikka Huusari <>
Submitted on : Wednesday, July 17, 2019 - 4:16:07 PM
Last modification on : Friday, July 19, 2019 - 1:27:30 AM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02187162, version 1

Collections

Citation

Riikka Huusari, Hachem Kadri. Entangled Kernels. International Joint Conference of Artificial Intelligence, Aug 2019, Macao, China. ⟨hal-02187162⟩

Share

Metrics

Record views

36

Files downloads

39