TY - JOUR
T1 - Online Learning versus Offline Learning
AU - Ben-David, Shai
AU - Kushilevitz, Eyal
AU - Mansour, Yishay
N1 - Funding Information:
* This paper is an extended version of a paper that appeared in EuroCOLT 1995. In addition it contains some of the results of the paper “On Self-Directed Learning” by S. Ben-David, N. Eiron, and E. Kushilevitz that appeared in COLT 1995. ** http://www.cs.technion.ac.il/»eyalk. This research was supported by Technion V.P.R. Fund 120-872 and by Japan Technion Society Research Fund. y http://www.math.tau.ac.il/ mansour. This research was supported in part by The Israel Science Foundation administered by the Israel Academy of Science and Humanities, and by a grant of the Israeli Ministry of Science and Technology.
PY - 1997
Y1 - 1997
N2 - We present an off-line variant of the mistake-bound model of learning. This is an intermediate model between the on-line learning model (Littlestone, 1988, Littlestone, 1989) and the self-directed learning model (Goldman, Rivest & Schapire, 1993, Goldman & Sloan, 1994). Just like in the other two models, a learner in the off-line 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 on-line model only the set of possible elements is known, in the off-line 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 self-directed learner, which is allowed to choose adaptively the sequence of elements presented to him. We study some of the fundamental properties of the off-line model. In particular, we compare the number of mistakes made by the off-line learner on certain concept classes to those made by the on-line and self-directed 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.
AB - We present an off-line variant of the mistake-bound model of learning. This is an intermediate model between the on-line learning model (Littlestone, 1988, Littlestone, 1989) and the self-directed learning model (Goldman, Rivest & Schapire, 1993, Goldman & Sloan, 1994). Just like in the other two models, a learner in the off-line 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 on-line model only the set of possible elements is known, in the off-line 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 self-directed learner, which is allowed to choose adaptively the sequence of elements presented to him. We study some of the fundamental properties of the off-line model. In particular, we compare the number of mistakes made by the off-line learner on certain concept classes to those made by the on-line and self-directed 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.
KW - Mistake-Bound
KW - On-Line Learning
KW - Rank of Trees
UR - http://www.scopus.com/inward/record.url?scp=0031245162&partnerID=8YFLogxK
U2 - 10.1023/A:1007465907571
DO - 10.1023/A:1007465907571
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:0031245162
SN - 0885-6125
VL - 29
SP - 45
EP - 63
JO - Machine Learning
JF - Machine Learning
IS - 1
ER -