Entangled Kernels -- Beyond Separability

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.

References in corpus (9)

• Scikit-learn: Machine Learning in Python
• Separability Criterion for Density Matrices
• Separability criterion and inseparable mixed states with positive partial transposition
• Algorithms for Learning Kernels Based on Centered Alignment
• A Riemannian Network for SPD Matrix Learning
• Operator-valued Kernels for Learning from Functional Response Data
• Convex Learning of Multiple Tasks and their Structure
• Efficient Output Kernel Learning for Multiple Tasks
• Operator-Valued Bochner Theorem, Fourier Feature Maps for Operator-Valued Kernels, and Vector-Valued Learning