Difference between revisions of "Martins et al 2010"
From Cohen Courses
Jump to navigationJump to search| Line 8: | Line 8: | ||
=== Method === | === Method === | ||
| + | |||
| + | The general loss function that they use is: | ||
| + | |||
| + | [[file:Martins et al 2010 Loss Function.png]] | ||
| + | |||
| + | Different choices of <math>\Beta</math> and <math>\gamma</math> correspond to various well known loss functions. They are: | ||
| + | |||
| + | [[file:Martins et al 2010 Parameter Choices.png]] | ||
| + | |||
=== Experimental Result === | === Experimental Result === | ||
Revision as of 20:36, 1 October 2011
Citation and Online Link
A. F. T. Martins, K. Gimpel. N. A. Smith, E. P. Xing, P. M. Q. Aguiar, M. A. T. Figueiredo, 2010. Aggressive Online Learning of Structured Classifiers. Technical report CMU-ML-10-109.
Summary
This paper generalizes the loss function of CRFs, structured SVMs, structured perceptron, and Softmax-margin CRFs into a single loss function, and then derives an online learning algorithm that can be used to learn with that more general loss function. For the hinge loss, the learning algorithm reduces to MIRA.
Method
The general loss function that they use is:
Different choices of and correspond to various well known loss functions. They are:
Experimental Result
Related Papers
MIRA CRF Softmax-margin CRFs
In progress by User:Jmflanig
