Work

Statistical and Computational Trade-Offs in Kernel K-Means

Year: 2019

Type: preprint

Abstract: We investigate the efficiency of k-means in terms of both statistical and computational requirements. More precisely, we study a Nyström approach to kernel k-means. We analyze the statistical properties of the proposed method and show that it achieves the same accuracy of exact kernel k-means with only a fraction of computations. Indeed, we prove under basic assumptions that sampling $\sqrt{n}$ Nyström landmarks allows to greatly reduce computational costs without incurring in any loss of accuracy. To the best of our knowledge this is the first result of this kind for unsupervised learning.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1908.10284

Authors: Calandriello, Daniele, Rosasco, Lorenzo

Institutions: Institut national de recherche en sciences et technologies du numérique, University of Genoa

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2891583539

Cites:

Cited by: 20

Related to: 20