skip to content
A general agnostic active learning algorithm Preview this item
ClosePreview this item
Checking...

A general agnostic active learning algorithm

Author: Sanjoy Dasgupta; Daniel Hsu; Claire Monteleoni
Publisher: [La Jolla, Calif.] : Dept. of Computer Science and Engineering, University of California, San Diego, [2007]
Series: Technical report (University of California, San Diego. Department of Computer Science and Engineering), no. CS07-898.
Edition/Format:   eBook : Document : English
Database:WorldCat
Summary:
We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of Cohn, Atlas, and Ladner to the agnostic setting, by (1) reformulating it using a reduction to supervised learning and (2) showing how to apply generalization bounds even for the non-i.i.d. samples that result from selective sampling. We  Read more...
Rating:

(not yet rated) 0 with reviews - Be the first.

Subjects
More like this

 

Find a copy online

Find a copy in the library

&AllPage.SpinnerRetrieving; Finding libraries that hold this item...

Details

Material Type: Document, Internet resource
Document Type: Internet Resource, Computer File
All Authors / Contributors: Sanjoy Dasgupta; Daniel Hsu; Claire Monteleoni
OCLC Number: 781856805
Description: 1 online resource (12 pages) : illustrations
Details: System requirements: PostScript.
Series Title: Technical report (University of California, San Diego. Department of Computer Science and Engineering), no. CS07-898.
Responsibility: Sanjoy Dasgupta, Daniel Hsu and Claire Monteleoni.

Abstract:

We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of Cohn, Atlas, and Ladner to the agnostic setting, by (1) reformulating it using a reduction to supervised learning and (2) showing how to apply generalization bounds even for the non-i.i.d. samples that result from selective sampling. We provide a general characterization of the label complexity of our algorithm. This quantity is never more than the usual PAC sample complexity of supervised learning, and is exponentially smaller for some hypothesis classes and distributions. We also demonstrate improvements experimentally.

Reviews

User-contributed reviews
Retrieving GoodReads reviews...
Retrieving DOGObooks reviews...

Tags

Be the first.
Confirm this request

You may have already requested this item. Please select Ok if you would like to proceed with this request anyway.

Linked Data


<http://www.worldcat.org/oclc/781856805>
library:oclcnum"781856805"
library:placeOfPublication
library:placeOfPublication
owl:sameAs<info:oclcnum/781856805>
rdf:typeschema:Book
schema:about
schema:about
schema:about
schema:bookFormatschema:EBook
schema:contributor
schema:contributor
schema:creator
schema:datePublished"2007"
schema:description"We present a simple, agnostic active learning algorithm that works for any hypothesis class of bounded VC dimension, and any data distribution. Our algorithm extends a scheme of Cohn, Atlas, and Ladner to the agnostic setting, by (1) reformulating it using a reduction to supervised learning and (2) showing how to apply generalization bounds even for the non-i.i.d. samples that result from selective sampling. We provide a general characterization of the label complexity of our algorithm. This quantity is never more than the usual PAC sample complexity of supervised learning, and is exponentially smaller for some hypothesis classes and distributions. We also demonstrate improvements experimentally."@en
schema:exampleOfWork<http://worldcat.org/entity/work/id/1096050267>
schema:inLanguage"en"
schema:name"A general agnostic active learning algorithm"@en
schema:publisher
schema:url
schema:url<http://csetechrep.ucsd.edu/Dienst/UI/2.0/Describe/ncstrl.ucsd_cse/CS2007-0898>
schema:url<http://bibpurl.oclc.org/web/45757/CS2007-0898>

Content-negotiable representations

Close Window

Please sign in to WorldCat 

Don't have an account? You can easily create a free account.