Skip navigation
Skip navigation

Tighter bounds for structured estimation

Chapelle, Olivier; Do, Chuong B.; Le, Quoc Viet; Smola, Alexander; Teo, Choon-Hui


Large-margin structured estimation methods minimize a convex upper bound of loss functions. While they allow for efficient optimization algorithms, these convex formulations are not tight and sacrifice the ability to accurately model the true loss. We present tighter non-convex bounds based on generalizing the notion of a ramp loss from binary classification to structured estimation. We show that a small modification of existing optimization algorithms suffices to solve this modified problem....[Show more]

CollectionsANU Research Publications
Date published: 2008
Type: Conference paper
Source: Advances in Neural Information Processing Systems 21


File Description SizeFormat Image
01_Chapelle_Tighter_bounds_for_structured_2008.pdf28.6 kBAdobe PDF    Request a copy
02_Chapelle_Tighter_bounds_for_structured_2008.pdf233.94 kBAdobe PDF    Request a copy
03_Chapelle_Tighter_bounds_for_structured_2008.pdf16.71 kBAdobe PDF    Request a copy

Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator