Convex learning with invariances

Choon Hui Teo; Amir Globerson; Sam Roweis; Alexander J. Smola

Convex learning with invariances

Choon Hui Teo^*, Amir Globerson, Sam Roweis, Alexander J. Smola

^*Corresponding author for this work

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

Abstract

Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization algorithms for kernels, including solvers of the SVMStruct family. The advantage of our setting is that it relies on column generation instead of modifying the underlying optimization problem directly.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
Publisher	Curran Associates Inc.
ISBN (Print)	160560352X, 9781605603520
State	Published - 2008
Externally published	Yes
Event	21st Annual Conference on Neural Information Processing Systems, NIPS 2007 - Vancouver, BC, Canada Duration: 3 Dec 2007 → 6 Dec 2007

Publication series

Name	Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

Conference

Conference	21st Annual Conference on Neural Information Processing Systems, NIPS 2007
Country/Territory	Canada
City	Vancouver, BC
Period	3/12/07 → 6/12/07

Cite this

@inproceedings{15bc6e36e2564eed90e3f0e33cb1e402,

title = "Convex learning with invariances",

abstract = "Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization algorithms for kernels, including solvers of the SVMStruct family. The advantage of our setting is that it relies on column generation instead of modifying the underlying optimization problem directly.",

author = "Teo, {Choon Hui} and Amir Globerson and Sam Roweis and Smola, {Alexander J.}",

year = "2008",

language = "אנגלית",

isbn = "160560352X",

series = "Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference",

publisher = "Curran Associates Inc.",

booktitle = "Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference",

note = "null ; Conference date: 03-12-2007 Through 06-12-2007",

}

Teo, CH, Globerson, A, Roweis, S & Smola, AJ 2008, Convex learning with invariances. in Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference, Curran Associates Inc., 21st Annual Conference on Neural Information Processing Systems, NIPS 2007, Vancouver, BC, Canada, 3/12/07.

Convex learning with invariances. / Teo, Choon Hui; Globerson, Amir; Roweis, Sam et al.

Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference. Curran Associates Inc., 2008. (Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference).

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

TY - GEN

T1 - Convex learning with invariances

AU - Teo, Choon Hui

AU - Globerson, Amir

AU - Roweis, Sam

AU - Smola, Alexander J.

PY - 2008

Y1 - 2008

N2 - Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization algorithms for kernels, including solvers of the SVMStruct family. The advantage of our setting is that it relies on column generation instead of modifying the underlying optimization problem directly.

AB - Incorporating invariances into a learning algorithm is a common problem in machine learning. We provide a convex formulation which can deal with arbitrary loss functions and arbitrary losses. In addition, it is a drop-in replacement for most optimization algorithms for kernels, including solvers of the SVMStruct family. The advantage of our setting is that it relies on column generation instead of modifying the underlying optimization problem directly.

UR - http://www.scopus.com/inward/record.url?scp=85138473786&partnerID=8YFLogxK

M3 - פרסום בספר כנס

AN - SCOPUS:85138473786

SN - 160560352X

SN - 9781605603520

T3 - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

BT - Advances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

PB - Curran Associates Inc.

Y2 - 3 December 2007 through 6 December 2007

ER -

Convex learning with invariances

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this