← Back to papers
2008 JMLR JMLR 2008

On the Equivalence of Linear Dimensionality-Reducing Transformations

Abstract

In this JMLR volume, Ye (2008) demonstrates the essential equivalence of two sets of solutions to a generalized Fisher criterion used for linear dimensionality reduction (see Ye, 2005; Loog, 2007). Here, I point out the basic flaw in this new contribution. [abs] [ pdf ][ bib ] © JMLR 2008. (edit, beta)

🌉 Interdisciplinary Bridge — Machine Learning and Mathematics & Optimization
📈 Trend Setter — Linear Algebra
🧭 Keyword Pioneer — linear dimensionality reduction
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Security & Privacy

Authors

Marco Loog

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Optimization & Theory > Theory Mathematics & Optimization > Mathematics > Linear Algebra Machine Learning > Core Methods > Dimensionality Reduction

Keywords

generalized eigenvalue problem linear algebra linear dimensionality reduction fisher criterion dimensionality-reducing transformation
Download PDF

Related papers

Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies 2008
Algorithms for Sparse Linear Classifiers in the Massive Data Setting 2008
Graphical Methods for Efficient Likelihood Inference in Gaussian Covariance Models 2008
Shark 2008
Consistency of Trace Norm Minimization 2008