Learnability and stability in the general learning setting

Shai Shalev-Shwartz; Ohad Shamir; Nathan Srebro; Karthik Sridharan

Learnability and stability in the general learning setting

Shai Shalev-Shwartz, Ohad Shamir, Nathan Srebro, Karthik Sridharan

Research output: Contribution to conference › Paper › peer-review

11 Scopus citations

Abstract

We establish that stability is necessary and sufficient for learning, even in the General Learning Setting where uniform convergence conditions are not necessary for learning, and where learning might only be possible with a non-ERM learning rule. This goes beyond previous work on the relationship between stability and learnability, which focused on supervised classification and regression, where learnability is equivalent to uniform convergence and it is enough to consider the ERM.

Original language	English
State	Published - 2009
Externally published	Yes
Event	22nd Conference on Learning Theory, COLT 2009 - Montreal, QC, Canada Duration: 18 Jun 2009 → 21 Jun 2009

Conference

Conference	22nd Conference on Learning Theory, COLT 2009
Country/Territory	Canada
City	Montreal, QC
Period	18/06/09 → 21/06/09

Cite this

@conference{75ce0455463140639391dc9b6e997b38,

title = "Learnability and stability in the general learning setting",

abstract = "We establish that stability is necessary and sufficient for learning, even in the General Learning Setting where uniform convergence conditions are not necessary for learning, and where learning might only be possible with a non-ERM learning rule. This goes beyond previous work on the relationship between stability and learnability, which focused on supervised classification and regression, where learnability is equivalent to uniform convergence and it is enough to consider the ERM.",

author = "Shai Shalev-Shwartz and Ohad Shamir and Nathan Srebro and Karthik Sridharan",

year = "2009",

language = "אנגלית",

note = "22nd Conference on Learning Theory, COLT 2009 ; Conference date: 18-06-2009 Through 21-06-2009",

}

TY - CONF

T1 - Learnability and stability in the general learning setting

AU - Shalev-Shwartz, Shai

AU - Shamir, Ohad

AU - Srebro, Nathan

AU - Sridharan, Karthik

PY - 2009

Y1 - 2009

N2 - We establish that stability is necessary and sufficient for learning, even in the General Learning Setting where uniform convergence conditions are not necessary for learning, and where learning might only be possible with a non-ERM learning rule. This goes beyond previous work on the relationship between stability and learnability, which focused on supervised classification and regression, where learnability is equivalent to uniform convergence and it is enough to consider the ERM.

AB - We establish that stability is necessary and sufficient for learning, even in the General Learning Setting where uniform convergence conditions are not necessary for learning, and where learning might only be possible with a non-ERM learning rule. This goes beyond previous work on the relationship between stability and learnability, which focused on supervised classification and regression, where learnability is equivalent to uniform convergence and it is enough to consider the ERM.

UR - http://www.scopus.com/inward/record.url?scp=84898079331&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontoconference.paper???

AN - SCOPUS:84898079331

T2 - 22nd Conference on Learning Theory, COLT 2009

Y2 - 18 June 2009 through 21 June 2009

ER -

Learnability and stability in the general learning setting

Abstract

Conference

Other files and links

Fingerprint

Cite this