Learning Convex Bodies under uniform distribution

Walter Kern

doi:10.1016/0020-0190(92)90026-R

Learning Convex Bodies under uniform distribution

Walter Kern

Discrete Mathematics and Mathematical Programming

Research output: Contribution to journal › Article › Academic › peer-review

269 Downloads (Pure)

Abstract

We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.

Original language	Undefined
Pages (from-to)	35-39
Number of pages	5
Journal	Information processing letters
Volume	0
Issue number	43
DOIs	https://doi.org/10.1016/0020-0190(92)90026-R
Publication status	Published - 1992

Keywords

Theory of computation
convex bodies
METIS-140518
uniform distribution
IR-29884
learning by example

Access to Document

10.1016/0020-0190(92)90026-R

Kern92learning

Cite this

@article{22814fcc05a4407c818cb3e0b702c7d7,

title = "Learning Convex Bodies under uniform distribution",

abstract = "We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.",

keywords = "Theory of computation, convex bodies, METIS-140518, uniform distribution, IR-29884, learning by example",

author = "Walter Kern",

year = "1992",

doi = "10.1016/0020-0190(92)90026-R",

language = "Undefined",

volume = "0",

pages = "35--39",

journal = "Information processing letters",

issn = "0020-0190",

publisher = "Elsevier",

number = "43",

}

TY - JOUR

T1 - Learning Convex Bodies under uniform distribution

AU - Kern, Walter

PY - 1992

Y1 - 1992

N2 - We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.

AB - We prove that the class of convex bodies contained in a fixed (prescribed) bounded region R c lQd is PAC-learnable, if the positive examples are drawn according to the uniform distribution Df on the target concept (the distribution Dm on the negative examples may be arbitrary). Our results extend previous work by E. Baum.

KW - Theory of computation

KW - convex bodies

KW - METIS-140518

KW - uniform distribution

KW - IR-29884

KW - learning by example

U2 - 10.1016/0020-0190(92)90026-R

DO - 10.1016/0020-0190(92)90026-R

M3 - Article

SN - 0020-0190

VL - 0

SP - 35

EP - 39

JO - Information processing letters

JF - Information processing letters

IS - 43

ER -