Leveraged vector machines

Yoram Singer

Leveraged vector machines

Yoram Singer

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

Abstract

We describe an iterative algorithm for building vector machines used in classification tasks. The algorithm builds on ideas from support vector machines, boosting, and generalized additive models. The algorithm can be used with various continuously differential functions that bound the discrete (0-1) classification loss and is very simple to implement. We test the proposed algorithm with two different loss functions on synthetic and natural data. We also describe a norm-penalized version of the algorithm for the exponential loss function used in AdaBoost. The performance of the algorithm on natural data is comparable to support vector machines while typically its running time is shorter than of SVM.

Original language	English (US)
Title of host publication	Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999
Publisher	Neural information processing systems foundation
Pages	610-616
Number of pages	7
ISBN (Print)	0262194503, 9780262194501
State	Published - 2000
Event	13th Annual Neural Information Processing Systems Conference, NIPS 1999 - Denver, CO, United States Duration: Nov 29 1999 → Dec 4 1999

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Other

Other	13th Annual Neural Information Processing Systems Conference, NIPS 1999
Country/Territory	United States
City	Denver, CO
Period	11/29/99 → 12/4/99

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

@inproceedings{b88431c989d94c1299e9e3703efc3cbb,

title = "Leveraged vector machines",

abstract = "We describe an iterative algorithm for building vector machines used in classification tasks. The algorithm builds on ideas from support vector machines, boosting, and generalized additive models. The algorithm can be used with various continuously differential functions that bound the discrete (0-1) classification loss and is very simple to implement. We test the proposed algorithm with two different loss functions on synthetic and natural data. We also describe a norm-penalized version of the algorithm for the exponential loss function used in AdaBoost. The performance of the algorithm on natural data is comparable to support vector machines while typically its running time is shorter than of SVM.",

author = "Yoram Singer",

year = "2000",

language = "English (US)",

isbn = "0262194503",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "610--616",

booktitle = "Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999",

note = "13th Annual Neural Information Processing Systems Conference, NIPS 1999 ; Conference date: 29-11-1999 Through 04-12-1999",

}

Singer, Y 2000, Leveraged vector machines. in Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999. Advances in Neural Information Processing Systems, Neural information processing systems foundation, pp. 610-616, 13th Annual Neural Information Processing Systems Conference, NIPS 1999, Denver, CO, United States, 11/29/99.

TY - GEN

T1 - Leveraged vector machines

AU - Singer, Yoram

PY - 2000

Y1 - 2000

N2 - We describe an iterative algorithm for building vector machines used in classification tasks. The algorithm builds on ideas from support vector machines, boosting, and generalized additive models. The algorithm can be used with various continuously differential functions that bound the discrete (0-1) classification loss and is very simple to implement. We test the proposed algorithm with two different loss functions on synthetic and natural data. We also describe a norm-penalized version of the algorithm for the exponential loss function used in AdaBoost. The performance of the algorithm on natural data is comparable to support vector machines while typically its running time is shorter than of SVM.

AB - We describe an iterative algorithm for building vector machines used in classification tasks. The algorithm builds on ideas from support vector machines, boosting, and generalized additive models. The algorithm can be used with various continuously differential functions that bound the discrete (0-1) classification loss and is very simple to implement. We test the proposed algorithm with two different loss functions on synthetic and natural data. We also describe a norm-penalized version of the algorithm for the exponential loss function used in AdaBoost. The performance of the algorithm on natural data is comparable to support vector machines while typically its running time is shorter than of SVM.

UR - http://www.scopus.com/inward/record.url?scp=0006413386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0006413386&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0006413386

SN - 0262194503

SN - 9780262194501

T3 - Advances in Neural Information Processing Systems

SP - 610

EP - 616

BT - Advances in Neural Information Processing Systems 12 - Proceedings of the 1999 Conference, NIPS 1999

PB - Neural information processing systems foundation

T2 - 13th Annual Neural Information Processing Systems Conference, NIPS 1999

Y2 - 29 November 1999 through 4 December 1999

ER -

Leveraged vector machines

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this