@InProceedings{	  frank.ea:selecting:2011,
  abstract	= {Truncated Singular Value Decomposition (SVD) calculates
		  the closest rank-$k$ approximation of a given input matrix.
		  Selecting the appropriate rank $k$ defines a critical model
		  order choice in most applications of SVD. To obtain a
		  principled cut-off criterion for the spectrum, we convert
		  the underlying optimization problem into a noisy channel
		  coding problem. The optimal approximation capacity ofthis
		  channel controls the appropriate strength of regularization
		  to suppress noise. In simulation experiments, this
		  information theoretic method to determine the optimal rank
		  competes with state-of-the art model selection
		  techniques.},
  author	= {Mario Frank and Joachim M. Buhmann},
  booktitle	= {ISIT 2011: IEEE International Symposium on Information
		  Theory },
  copyright	= {IEEE},
  language	= {USenglish},
  month		= {Aug},
  publisher	= {IEEE},
  title		= {Selecting the rank of truncated SVD by Maximum
		  Approximation Capacity},
  url		= {http://arxiv.org/abs/1102.3176},
  year		= 2011,
  user		= {mafrank}
}