Work

Rademacher processes and bounding the risk of function learning

Year: 2004

Type: preprint

Abstract: We construct data dependent bounds on the risk in function learning problems. The bounds are based on the local norms of the Rademacher process indexed by the underlying function class and they do not require prior knowledge about the distribution of the training examples or any specific properties of the function class.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.math/0405338

Authors: Koltchinskii, Vladimir, Panchenko, Dmitry

Institution: University of New Mexico

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4394670702

Cites:

Cited by:

Related to: 10