LGCAJul 21, 2023

Mercer Large-Scale Kernel Machines from Ridge Function Perspective

arXiv:2307.11925v22.0h-index: 7
Originality Synthesis-oriented
AI Analysis

This work provides theoretical insights into kernel approximations for machine learning, but it appears incremental as it builds on existing approximation theory results.

The paper analyzes large-scale kernel machines from a ridge function perspective, identifying obstacles in approximating kernels with sums of cosine products and applying the results to image processing using a one-vs-rest procedure.

To present Mercer large-scale kernel machines from a ridge function perspective, we recall the results by Lin and Pinkus from {\it Fundamentality of ridge functions}. We consider the main result of the recent paper by Rachimi and Recht, 2008, {\it Random features for large-scale kernel machines} from the Approximation Theory point of view. We study which kernels could be approximated by a sum of products of cosine functions with arguments depending on $x$ and $y$ and present the obstacles of such an approach. The results of this article are applied to Image Processing by procedure "one-vs-rest".

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes