Linear Dependent Dimensionality Reduction

We formulate linear dimensionality reduction as a semi-parametric estimation problem, enabling us to study its asymptotic behavior. We generalize the problem beyond additive Gaussian noise to (unknown) nonGaussian additive noise, and to unbiased non-additive models.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Nathan Srebro, Tommi Jaakkola
• Keywords: Additive Gaussian Noise, Linear Dimensionality Reduction, NIPS 2003, NIPS 2007, NonGaussian Additive Noise