Predicting nearly as well as the best pruning of a planar decision graph

Eiji Takimoto; Manfred K. Warmuth

doi:10.1016/S0304-3975(01)00401-7

Predicting nearly as well as the best pruning of a planar decision graph

Eiji Takimoto, Manfred K. Warmuth

Research output: Contribution to journal › Conference article

14 Citations (Scopus)

Abstract

We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.

Original language	English
Pages (from-to)	217-235
Number of pages	19
Journal	Theoretical Computer Science
Volume	288
Issue number	2
DOIs	https://doi.org/10.1016/S0304-3975(01)00401-7
Publication status	Published - Oct 16 2002
Externally published	Yes
Event	Algorithmic Learning Theory (ALT 1999) - Tokyo, Japan Duration: Dec 6 1999 → Dec 8 1999

Fingerprint

All Science Journal Classification (ASJC) codes

Theoretical Computer Science
Computer Science(all)

Cite this

Takimoto, E., & Warmuth, M. K. (2002). Predicting nearly as well as the best pruning of a planar decision graph. Theoretical Computer Science, 288(2), 217-235. https://doi.org/10.1016/S0304-3975(01)00401-7

@article{2e65d87366fc465583e0b55d81235e90,

title = "Predicting nearly as well as the best pruning of a planar decision graph",

abstract = "We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.",

author = "Eiji Takimoto and Warmuth, {Manfred K.}",

year = "2002",

month = "10",

day = "16",

doi = "10.1016/S0304-3975(01)00401-7",

language = "English",

volume = "288",

pages = "217--235",

journal = "Theoretical Computer Science",

issn = "0304-3975",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Predicting nearly as well as the best pruning of a planar decision graph

AU - Takimoto, Eiji

AU - Warmuth, Manfred K.

PY - 2002/10/16

Y1 - 2002/10/16

N2 - We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.

AB - We design efficient on-line algorithms that predict nearly as well as the best pruning of a planar decision graph. We assume that the graph has no cycles. As in the previous work on decision trees, we implicitly maintain one weight for each of the prunings (exponentially many). The method works for a large class of algorithms that update its weights multiplicatively. It can also be used to design algorithms that predict nearly as well as the best convex combination of prunings.

UR - http://www.scopus.com/inward/record.url?scp=0037120731&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037120731&partnerID=8YFLogxK

U2 - 10.1016/S0304-3975(01)00401-7

DO - 10.1016/S0304-3975(01)00401-7

M3 - Conference article

AN - SCOPUS:0037120731

VL - 288

SP - 217

EP - 235

JO - Theoretical Computer Science

JF - Theoretical Computer Science

SN - 0304-3975

IS - 2

ER -

Access to Document

10.1016/S0304-3975(01)00401-7