CHIRP: A new classifier based on composite hypercubes on iterated random projections

Leland Wilkinson; Anushka Anand; Dang Nhon Tuan

doi:10.1145/2020408.2020418

CHIRP: A new classifier based on composite hypercubes on iterated random projections

Leland Wilkinson, Anushka Anand, Dang Nhon Tuan

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

26 Scopus citations

Abstract

We introduce a classifier based on the L_∞ norm. This classifier, called CHIRP, is an iterative sequence of three stages (projecting, binning, and covering) that are designed to deal with the curse of dimensionality, computational complexity, and nonlinear separability. CHIRP is not a hybrid or modification of existing classifiers; it employs a new covering algorithm. The accuracy of CHIRP on widely-used benchmark datasets exceeds the accuracy of competitors. Its computational complexity is sub-linear in number of instances and number of variables and subquadratic in number of classes.

Original language	English
Title of host publication	Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11
Pages	6-14
Number of pages	9
DOIs	https://doi.org/10.1145/2020408.2020418
State	Published - 2011
Event	17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11 - San Diego, CA, United States Duration: Aug 21 2011 → Aug 24 2011

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11
Country/Territory	United States
City	San Diego, CA
Period	08/21/11 → 08/24/11

Keywords

Random projections
Supervised classification

Access to Document

10.1145/2020408.2020418

Cite this

Wilkinson, L., Anand, A., & Tuan, D. N. (2011). CHIRP: A new classifier based on composite hypercubes on iterated random projections. In Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11 (pp. 6-14). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). https://doi.org/10.1145/2020408.2020418

@inproceedings{2776f2f2703944e592677fbcd3ad4eee,

title = "CHIRP: A new classifier based on composite hypercubes on iterated random projections",

abstract = "We introduce a classifier based on the L∞ norm. This classifier, called CHIRP, is an iterative sequence of three stages (projecting, binning, and covering) that are designed to deal with the curse of dimensionality, computational complexity, and nonlinear separability. CHIRP is not a hybrid or modification of existing classifiers; it employs a new covering algorithm. The accuracy of CHIRP on widely-used benchmark datasets exceeds the accuracy of competitors. Its computational complexity is sub-linear in number of instances and number of variables and subquadratic in number of classes.",

keywords = "Random projections, Supervised classification",

author = "Leland Wilkinson and Anushka Anand and Tuan, {Dang Nhon}",

year = "2011",

doi = "10.1145/2020408.2020418",

language = "English",

isbn = "9781450308137",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

pages = "6--14",

booktitle = "Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11",

note = "null ; Conference date: 21-08-2011 Through 24-08-2011",

}

Wilkinson, L, Anand, A & Tuan, DN 2011, CHIRP: A new classifier based on composite hypercubes on iterated random projections. in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 6-14, 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11, San Diego, CA, United States, 08/21/11. https://doi.org/10.1145/2020408.2020418

CHIRP : A new classifier based on composite hypercubes on iterated random projections. / Wilkinson, Leland; Anand, Anushka; Tuan, Dang Nhon.

Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11. 2011. p. 6-14 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CHIRP

AU - Wilkinson, Leland

AU - Anand, Anushka

AU - Tuan, Dang Nhon

PY - 2011

Y1 - 2011

N2 - We introduce a classifier based on the L∞ norm. This classifier, called CHIRP, is an iterative sequence of three stages (projecting, binning, and covering) that are designed to deal with the curse of dimensionality, computational complexity, and nonlinear separability. CHIRP is not a hybrid or modification of existing classifiers; it employs a new covering algorithm. The accuracy of CHIRP on widely-used benchmark datasets exceeds the accuracy of competitors. Its computational complexity is sub-linear in number of instances and number of variables and subquadratic in number of classes.

AB - We introduce a classifier based on the L∞ norm. This classifier, called CHIRP, is an iterative sequence of three stages (projecting, binning, and covering) that are designed to deal with the curse of dimensionality, computational complexity, and nonlinear separability. CHIRP is not a hybrid or modification of existing classifiers; it employs a new covering algorithm. The accuracy of CHIRP on widely-used benchmark datasets exceeds the accuracy of competitors. Its computational complexity is sub-linear in number of instances and number of variables and subquadratic in number of classes.

KW - Random projections

KW - Supervised classification

UR - http://www.scopus.com/inward/record.url?scp=80052682430&partnerID=8YFLogxK

U2 - 10.1145/2020408.2020418

DO - 10.1145/2020408.2020418

M3 - Conference contribution

AN - SCOPUS:80052682430

SN - 9781450308137

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 6

EP - 14

BT - Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD'11

Y2 - 21 August 2011 through 24 August 2011

ER -

CHIRP: A new classifier based on composite hypercubes on iterated random projections

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this