Active sampling for multiple output identification

Shai Fine; Yishay Mansour

doi:10.1007/s10994-007-5026-6

Active sampling for multiple output identification

Shai Fine^*, Yishay Mansour

^*Corresponding author for this work

School of Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.

Original language	English
Pages (from-to)	213-228
Number of pages	16
Journal	Machine Learning
Volume	69
Issue number	2-3
DOIs	https://doi.org/10.1007/s10994-007-5026-6
State	Published - Dec 2007

Keywords

Active learning
Active sampling
Hitting
Output identification
Separation dimension
Transductive learning
VC dimension

Access to Document

10.1007/s10994-007-5026-6

Cite this

@article{0a9865fe09fa441799be9036a241637a,

title = "Active sampling for multiple output identification",

abstract = "We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.",

keywords = "Active learning, Active sampling, Hitting, Output identification, Separation dimension, Transductive learning, VC dimension",

author = "Shai Fine and Yishay Mansour",

note = "Funding Information: This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778, by a grant No. 1079/04 from the Israel Science Foundation, by a grant from BSF and an IBM faculty award. This publication only reflects the authors{\textquoteright} views.",

year = "2007",

month = dec,

doi = "10.1007/s10994-007-5026-6",

language = "אנגלית",

volume = "69",

pages = "213--228",

journal = "Machine Learning",

issn = "0885-6125",

publisher = "Springer Netherlands",

number = "2-3",

}

TY - JOUR

T1 - Active sampling for multiple output identification

AU - Fine, Shai

AU - Mansour, Yishay

N1 - Funding Information: This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778, by a grant No. 1079/04 from the Israel Science Foundation, by a grant from BSF and an IBM faculty award. This publication only reflects the authors’ views.

PY - 2007/12

Y1 - 2007/12

N2 - We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.

AB - We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.

KW - Active learning

KW - Active sampling

KW - Hitting

KW - Output identification

KW - Separation dimension

KW - Transductive learning

KW - VC dimension

UR - http://www.scopus.com/inward/record.url?scp=35348892658&partnerID=8YFLogxK

U2 - 10.1007/s10994-007-5026-6

DO - 10.1007/s10994-007-5026-6

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:35348892658

SN - 0885-6125

VL - 69

SP - 213

EP - 228

JO - Machine Learning

JF - Machine Learning

IS - 2-3

ER -

Active sampling for multiple output identification

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this