Search improves label for active learning

Alina Beygelzimer; Daniel Hsu; John Langford; Chicheng Zhang

Search improves label for active learning

Alina Beygelzimer, Daniel Hsu, John Langford, Chicheng Zhang

Research output: Contribution to journal › Conference article › peer-review

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.

Original language	English (US)
Pages (from-to)	3350-3358
Number of pages	9
Journal	Advances in Neural Information Processing Systems
State	Published - 2016
Externally published	Yes
Event	30th Annual Conference on Neural Information Processing Systems, NIPS 2016 - Barcelona, Spain Duration: Dec 5 2016 → Dec 10 2016

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@article{365127066d1d4febb6e7bdbfc7788aca,

title = "Search improves label for active learning",

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.",

author = "Alina Beygelzimer and Daniel Hsu and John Langford and Chicheng Zhang",

note = "Publisher Copyright: {\textcopyright} 2016 NIPS Foundation - All Rights Reserved.; 30th Annual Conference on Neural Information Processing Systems, NIPS 2016 ; Conference date: 05-12-2016 Through 10-12-2016",

year = "2016",

language = "English (US)",

pages = "3350--3358",

journal = "Advances in Neural Information Processing Systems",

issn = "1049-5258",

publisher = "Neural information processing systems foundation",

}

TY - JOUR

T1 - Search improves label for active learning

AU - Beygelzimer, Alina

AU - Hsu, Daniel

AU - Langford, John

AU - Zhang, Chicheng

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85019181766&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019181766&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85019181766

SN - 1049-5258

SP - 3350

EP - 3358

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

T2 - 30th Annual Conference on Neural Information Processing Systems, NIPS 2016

Y2 - 5 December 2016 through 10 December 2016

ER -

Search improves label for active learning

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this