PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learnability and Stability in the General Learning Setting
Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan and Nathan Srebro
In: COLT 2009, 18-20 Jun 2009, Montreal.


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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:5420
Deposited By:Shai Shalev-Shwartz
Deposited On:02 July 2009