Bridging Algorithmic Information Theory and Machine Learning: A New Approach to Kernel Learning

arXiv:2311.12624v2 Announce Type: replace
Abstract: Machine Learning (ML) and Algorithmic Information Theory (AIT) look at Complexity from different points of view. We explore the interface between AIT and Kernel Methods (that are prevalent in ML) by adopting an AIT perspective on the problem of learning kernels from data, in kernel ridge regression, through the method of Sparse Kernel Flows. In particular, by looking at the differences and commonalities between Minimal Description Length (MDL) and Regularization in Machine Learning (RML), we …

abstract arxiv complexity cs.it cs.lg explore information kernel look machine machine learning math.it perspective stat.ml theory type view