Subspace, Latent Structure And Feature Selection

by Saunders, Craig; Grobelnik, Marko; Gunn, Steve; Shawe-Taylor, John

• ISBN13: 9783540341376
• ISBN10: 3540341374
• Format: Paperback
• Copyright: 2006-06-15
• Publisher: Springer-Verlag New York Inc

Summary

This book constitutes the thoroughly refereed post-proceedings of the PASCAL (pattern analysis, statistical modelling and computational learning) Statistical and Optimization Perspectives Workshop on Subspace, Latent Structure and Feature Selection techniques, SLSFS 2005, held in Bohinj, Slovenia in February 2005.The 9 revised full papers presented together with 5 invited papers were carefully selected during two rounds of reviewing and improvement for inclusion in the book. The papers reflect the key approaches that have been developed for subspace identification and feature selection using dimension reduction techniques, subspace methods, random projection methods, statistical analysis methods, Bayesian approaches to feature selection, latent structure analysis/probabilistic LSA, and optimisation methods.

Table of Contents

Invited Contributions
Discrete Component Analysis
Wray Buntine, Aleks Jakulin	1	(33)
Overview and Recent Advances in Partial Least Squares
Roman Rosipal, Nicole Krämer	34	(18)
Random Projection, Margins, Kernels, and Feature-Selection
Avrim Blum	52	(17)
Sonic Aspects of Latent Structure Analysis
D.M. Titterington	69	(15)
Feature Selection for Dimensionality Reduction
Dunja Mladenic	84	(19)
Contributed Papers
Auxiliary Variational Information Maximization for Dimensionality Reduction
Felix Agakov, David Barber	103	(12)
Constructing Visual Models with a Latent Space Approach
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez, Jean-Marc Odobez	115	(12)
Is Feature Selection Still Necessary?
Amir Navot, Ran Gilad-Bachrach, Yiftah Navot, Naftali Tishby	127	(12)
Class-Specific Subspace Discriminant Analysis for High-Dimensional Data
Charles Bouveyron, Stéphane Girard, Cordelia Schmid	139	(12)
Incorporating Constraints and Prior Knowledge into Factorization Algorithms - An Application to 3D Recovery
Amit Gruber, Yair Weiss	151	(12)
A Simple Feature Extraction for High Dimensional Image Representations
Christian Savu-Krohn, Peter Auer	163	(10)
Identifying Feature Relevance Using a Random Forest
Jeremy Rogers, Steve Gunn	173	(12)
Generalization Bounds for Subspace Selection and Hyperbolic PCA
Andreas Maurer	185	(13)
Less Biased Measurement of Feature Selection Benefits
Juha Reunanen	198	(11)
Author Index	209