Kernel Pre-Training in Feature Space via m-Kernels

05/21/2018

∙

This paper presents a novel approach to kernel tuning. The method presented borrows techniques from reproducing kernel Banach space (RKBS) theory and tensor kernels and leverages them to convert (re-weight in feature space) existing kernel functions into new, problem-specific kernels using auxiliary data. The proposed method is applied to accelerating Bayesian optimisation via covariance (kernel) function pre-tuning for short-polymer fibre manufacture and alloy design.

READ FULL TEXT

Kernel Pre-Training in Feature Space via m-Kernels

Covariance Function Pre-Training with m-Kernels for Accelerated Bayesian Optimisation

Kernel Methods for Nonlinear Connectivity Detection

Accelerating In-Browser Deep Learning Inference on Diverse Edge Clients through Just-in-Time Kernel Optimizations

Deep SimNets

Kernel-based Generative Learning in Distortion Feature Space

The role of feature space in atomistic learning

Semblance: A Rank-Based Kernel on Probability Spaces for Niche Detection

Kernel Pre-Training in Feature Space via m-Kernels

Related Research

Covariance Function Pre-Training with m-Kernels for Accelerated Bayesian Optimisation

Kernel Methods for Nonlinear Connectivity Detection

Accelerating In-Browser Deep Learning Inference on Diverse Edge Clients through Just-in-Time Kernel Optimizations

Deep SimNets

Kernel-based Generative Learning in Distortion Feature Space

The role of feature space in atomistic learning

Semblance: A Rank-Based Kernel on Probability Spaces for Niche Detection