Entangled Kernels - Beyond Separability

Riikka Huusari, Hachem Kadri

Research output: Contribution to journalArticleScientificpeer-review

2 Downloads (Pure)

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. We illustrate our algorithm with an application to supervised dimensionality reduction, and demonstrate its effectiveness with both artificial and real data for multi-output regression.
Original languageEnglish
Pages (from-to)1-40
Number of pages40
JournalJournal of Machine Learning Research
Volume22
Publication statusPublished - Jan 2021
MoE publication typeA1 Journal article-refereed

Fingerprint Dive into the research topics of 'Entangled Kernels - Beyond Separability'. Together they form a unique fingerprint.

Cite this