A Caltech Library Service

Improved Multi-Class Cost-Sensitive Boosting via Estimation of the Minimum-Risk Class

Appel, Ron and Burgos-Artizzu, Xavier P. and Perona, Pietro (2016) Improved Multi-Class Cost-Sensitive Boosting via Estimation of the Minimum-Risk Class. . (Unpublished)

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We present a simple unified framework for multi-class cost-sensitive boosting. The minimum-risk class is estimated directly, rather than via an approximation of the posterior distribution. Our method jointly optimizes binary weak learners and their corresponding output vectors, requiring classes to share features at each iteration. By training in a cost-sensitive manner, weak learners are invested in separating classes whose discrimination is important, at the expense of less relevant classification boundaries. Additional contributions are a family of loss functions along with proof that our algorithm is Boostable in the theoretical sense, as well as an efficient procedure for growing decision trees for use as weak learners. We evaluate our method on a variety of datasets: a collection of synthetic planar data, common UCI datasets, MNIST digits, SUN scenes, and CUB-200 birds. Results show state-of-the-art performance across all datasets against several strong baselines, including non-boosting multi-class approaches.

Item Type:Report or Paper (Discussion Paper)
Perona, Pietro0000-0002-7583-5809
Contact Email
Additional Information:Includes Supplementary Material.
Record Number:CaltechAUTHORS:20160922-125241569
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:70538
Deposited By: SWORD User
Deposited On:22 Sep 2016 20:28
Last Modified:03 Oct 2019 10:31

Repository Staff Only: item control page