Work

Search Improves Label for Active Learning

Year: 2016

Type: preprint

Abstract: We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human searches a database to seed or counterexample an existing solution. Search is stronger than Label while being natural to implement in many situations. We show that an algorithm using both oracles can provide exponentially large problem-dependent improvements over Label alone.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1602.07265

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

Institutions: Columbia University, Microsoft (United States), Microsoft Research New York City (United States), University of California San Diego

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2276364677

Cites: 20

Cited by: 14

Related to: 20