Feature Selection - Supplemental material

Lecture slides

Good general survey:

Applications:

• Ben Liblit et al (2005). Scalable Statistical Bug Isolation. Identifying software bugs by feature selection. Uses several of the techniques discussed in class, tailored to the specific task domain.
• E. P. Xing, M. I. Jordan, R. M. Karp (2001). Feature selection for high-dimensional genomic microarray data. Comparison of filter methods (including Markov blanket) with regularization methods for classification with high-dimensional microarray data.

Filtering:

• Y. Yang, J.P. Pedersen (1997). A comparative study on feature selection in text categorization.
• D. Koller, M. Sahami (1996). Toward optimal feature selection. Introduces the Markov blanket filtering method.

Wrappers:

• R. Kohavi, G. John (1997). Wrappers for feature subset selection. Survey of wrapper methods.

Regularization:

• R. Tibshirani (1996). Regression shrinkage and selection via the lasso. L1 regularized linear regression.
• B. Efron et al (2002). Least Angle Regression. Fast method for Lasso regression and forward stagewise search.

Kernel methods:

• H. Lodhi et al (2002). Text classification using string kernels. Good example of an efficiently-computable kernel with a huge implicit feature space.