Work

Agnostic Active Learning Without Constraints

Year: 2010

Type: preprint

Abstract: We present and analyze an agnostic active learning algorithm that works without keeping a version space. This is unlike all previous approaches where a restricted set of candidate hypotheses is maintained throughout learning, and only hypotheses from this set are ever returned. By avoiding this version space approach, our algorithm sheds the computational burden and brittleness associated with maintaining version spaces, yet still allows for substantial improvements over supervised learning for classification.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1006.2588

Authors: Beygelzimer, Alina, Hsu, Daniel, Langford, John, Zhang, Tong

Institutions: IBM (United States), Yahoo (United States), Rutgers, The State University of New Jersey, University of Pennsylvania

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1572210044

Cites: 22

Cited by: 131

Related to: 10