Online Learning versus Offline Learning
 Shai BenDavid,
 Eyal Kushilevitz,
 Yishay Mansour
 … show all 3 hide
Abstract
We present an offline variant of the mistakebound model of learning. This is an intermediate model between the online learning model (Littlestone, 1988, Littlestone, 1989) and the selfdirected learning model (Goldman, Rivest & Schapire, 1993, Goldman & Sloan, 1994). Just like in the other two models, a learner in the offline model has to learn an unknown concept from a sequence of elements of the instance space on which it makes “guess and test” trials. In all models, the aim of the learner is to make as few mistakes as possible. The difference between the models is that, while in the online model only the set of possible elements is known, in the offline model the sequence of elements (i.e., the identity of the elements as well as the order in which they are to be presented) is known to the learner in advance. On the other hand, the learner is weaker than the selfdirected learner, which is allowed to choose adaptively the sequence of elements presented to him.
We study some of the fundamental properties of the offline model. In particular, we compare the number of mistakes made by the offline learner on certain concept classes to those made by the online and selfdirected learners. We give bounds on the possible gaps between the various models and show examples that prove that our bounds are tight.
Another contribution of this paper is the extension of the combinatorial tool of labeled trees to a unified approach that captures the various mistake bound measures of all the models discussed. We believe that this tool will prove to be useful for further study of models of incremental learning.
 Title
 Online Learning versus Offline Learning
 Journal

Machine Learning
Volume 29, Issue 1 , pp 4563
 Cover Date
 199710
 DOI
 10.1023/A:1007465907571
 Print ISSN
 08856125
 Online ISSN
 15730565
 Publisher
 Kluwer Academic Publishers
 Additional Links
 Topics
 Keywords

 OnLine Learning
 MistakeBound
 Rank of Trees
 Industry Sectors
 Authors

 Shai BenDavid ^{(1)}
 Eyal Kushilevitz ^{(2)}
 Yishay Mansour ^{(3)}
 Author Affiliations

 1. Computer Science Dept., Technion, Israel
 2. Computer Science Dept., Technion, Israel
 3. Computer Science Dept., TelAviv University, Israel