Agnostic active learning without constraints

Alina Beygelzimer; Daniel Hsu; John Langford; Tong Zhang

Agnostic active learning without constraints

Alina Beygelzimer, Daniel Hsu, John Langford, Tong Zhang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 23
Subtitle of host publication	24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010
Publisher	Neural Information Processing Systems
ISBN (Print)	9781617823800
State	Published - 2010
Externally published	Yes
Event	24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 - Vancouver, BC, Canada Duration: Dec 6 2010 → Dec 9 2010

Publication series

Name	Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010

Conference

Conference	24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010
Country/Territory	Canada
City	Vancouver, BC
Period	12/6/10 → 12/9/10

ASJC Scopus subject areas

Information Systems

Library availability

Discover UIUC Full Text

Cite this

Beygelzimer, A., Hsu, D., Langford, J., & Zhang, T. (2010). Agnostic active learning without constraints. In Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 (Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010). Neural Information Processing Systems.

Agnostic active learning without constraints. / Beygelzimer, Alina; Hsu, Daniel; Langford, John et al.
Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010. Neural Information Processing Systems, 2010. (Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Beygelzimer, A, Hsu, D, Langford, J & Zhang, T 2010, Agnostic active learning without constraints. in Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010. Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010, Neural Information Processing Systems, 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010, Vancouver, BC, Canada, 12/6/10.

Beygelzimer A, Hsu D, Langford J, Zhang T. Agnostic active learning without constraints. In Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010. Neural Information Processing Systems. 2010. (Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010).

Beygelzimer, Alina ; Hsu, Daniel ; Langford, John et al. / Agnostic active learning without constraints. Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010. Neural Information Processing Systems, 2010. (Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010).

@inproceedings{ddb1d5fc12e64de1880f0edf5b2a06a4,

title = "Agnostic active learning without constraints",

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.",

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

year = "2010",

language = "English (US)",

isbn = "9781617823800",

series = "Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010",

publisher = "Neural Information Processing Systems",

booktitle = "Advances in Neural Information Processing Systems 23",

note = "24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010 ; Conference date: 06-12-2010 Through 09-12-2010",

}

TY - GEN

T1 - Agnostic active learning without constraints

AU - Beygelzimer, Alina

AU - Hsu, Daniel

AU - Langford, John

AU - Zhang, Tong

PY - 2010

Y1 - 2010

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85161966389&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85161966389&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85161966389

SN - 9781617823800

T3 - Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010

BT - Advances in Neural Information Processing Systems 23

PB - Neural Information Processing Systems

T2 - 24th Annual Conference on Neural Information Processing Systems 2010, NIPS 2010

Y2 - 6 December 2010 through 9 December 2010

ER -

Agnostic active learning without constraints

Abstract

Publication series

Conference

ASJC Scopus subject areas

Library availability

Related links

Fingerprint

Cite this