NDLI: On the efficient minimization of convex surrogates in supervised learning

Content Provider	IEEE Xplore Digital Library
Author	Nock, R. Nielseny, F.
Copyright Year	2008
Description	Author affiliation: LIX, Ecole Polytech., Palaiseau (Nielseny, F.) \|\| CEREGMIA, U. Antilles-Guyane, Schoelcher (Nock, R.)
Abstract	Bartlett et al (2006) recently proved that a ground condition for convex surrogates, classification calibration, ties up the minimization of the surrogates and classification risks, and left as important open problems the algorithmic questions about the minimization of these surrogates. Our paper gives an answer for a wide subset of these surrogates that we call ldquobalanced surrogatesrdquo, a set with popular members (logistic loss, squared loss), that contains all surrogates meeting three important requirements about classification. We propose an algorithm that fits linear separators to the minimization of any such surrogate, with guaranteed convergence bounds under a so-called ldquoweak learning assumptionrdquo, a generalization of the one that grounds celebrated boosting algorithms. Experiments on more than 50 readily available domains of 10 flavors of the algorithm display the performances of new surrogates.
Starting Page	1
Ending Page	4
File Size	503030
Page Count	4
File Format	PDF
ISBN	9781424421749
ISSN	10514651
DOI	10.1109/ICPR.2008.4761667
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2008-12-08
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Supervised learning Minimization methods Logistics Convergence Boosting Calibration Particle separators Displays Risk management Additives
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Bregman Divergences and Surrogates for Learning

Improving clustering algorithms through constrained convex optimization

On the efficient minimization of convex surrogates in supervised learning.

Boosting Invariance and Efficiency in Supervised Learning

On the Efficient Minimization of Convex Surrogates in Supervised Learning

On the efficient minimization of classification calibrated surrogates

Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization

On-line semi-supervised multiple-instance boosting

Robust Multiclass Ensemble Classifiers via Symmetric Functions

On the efficient minimization of convex surrogates in supervised learning

Similar Documents

Bregman Divergences and Surrogates for Learning

Improving clustering algorithms through constrained convex optimization

On the efficient minimization of convex surrogates in supervised learning.

Boosting Invariance and Efficiency in Supervised Learning

On the Efficient Minimization of Convex Surrogates in Supervised Learning

On the efficient minimization of classification calibrated surrogates

Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization

On-line semi-supervised multiple-instance boosting

Robust Multiclass Ensemble Classifiers via Symmetric Functions

On the efficient minimization of convex surrogates in supervised learning