pith. the verified trust layer for science. sign in

arxiv: 1207.1404 · v1 · pith:KU746S3Anew · submitted 2012-07-04 · 💻 cs.LG · cs.DS· stat.ML

A submodular-supermodular procedure with applications to discriminative structure learning

classification 💻 cs.LG cs.DSstat.ML
keywords informationlearningsubmodularapplicationsdifferencediscriminativegraphicalmodels
0
0 comments X p. Extension
Add this Pith Number to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{KU746S3A}

Prints a linked pith:KU746S3A badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

In this paper, we present an algorithm for minimizing the difference between two submodular functions using a variational framework which is based on (an extension of) the concave-convex procedure [17]. Because several commonly used metrics in machine learning, like mutual information and conditional mutual information, are submodular, the problem of minimizing the difference of two submodular problems arises naturally in many machine learning applications. Two such applications are learning discriminatively structured graphical models and feature selection under computational complexity constraints. A commonly used metric for measuring discriminative capacity is the EAR measure which is the difference between two conditional mutual information terms. Feature selection taking complexity considerations into account also fall into this framework because both the information that a set of features provide and the cost of computing and using the features can be modeled as submodular functions. This problem is NP-hard, and we give a polynomial time heuristic for it. We also present results on synthetic data to show that classifiers based on discriminative graphical models using this algorithm can significantly outperform classifiers based on generative graphical models.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.