Probabilistic Subspace Clustering Via Sparse Representations. Adler, A., Elad, M., & Hel-Or, Y. IEEE Signal Processing Letters, 20(1):63–66, January, 2013. Conference Name: IEEE Signal Processing Letters
doi  abstract   bibtex   
We present a probabilistic subspace clustering approach that is capable of rapidly clustering very large signal collections. Each signal is represented by a sparse combination of basis elements (atoms), which form the columns of a dictionary matrix. The set of sparse representations is utilized to derive the co-occurrences matrix of atoms and signals, which is modeled as emerging from a mixture model. The components of the mixture model are obtained via a non-negative matrix factorization (NNMF) of the co-occurrences matrix, and the subspace of each signal is estimated according to a maximum-likelihood (ML) criterion. Performance evaluation demonstrate comparable clustering accuracies to state-of-the-art at a fraction of the computational load.
@article{adler_probabilistic_2013,
	title = {Probabilistic {Subspace} {Clustering} {Via} {Sparse} {Representations}},
	volume = {20},
	issn = {1558-2361},
	doi = {10.1109/LSP.2012.2229705},
	abstract = {We present a probabilistic subspace clustering approach that is capable of rapidly clustering very large signal collections. Each signal is represented by a sparse combination of basis elements (atoms), which form the columns of a dictionary matrix. The set of sparse representations is utilized to derive the co-occurrences matrix of atoms and signals, which is modeled as emerging from a mixture model. The components of the mixture model are obtained via a non-negative matrix factorization (NNMF) of the co-occurrences matrix, and the subspace of each signal is estimated according to a maximum-likelihood (ML) criterion. Performance evaluation demonstrate comparable clustering accuracies to state-of-the-art at a fraction of the computational load.},
	language = {en},
	number = {1},
	journal = {IEEE Signal Processing Letters},
	author = {Adler, Amir and Elad, Michael and Hel-Or, Yacov},
	month = jan,
	year = {2013},
	note = {Conference Name: IEEE Signal Processing Letters},
	keywords = {\#Clustering, \#Representation, \#Sparse, \#Statistics, /unread, Accuracy, Aspect model, Clustering algorithms, Complexity theory, Dictionaries, Noise, Probabilistic logic, Sparse matrices, dictionary, non-negative matrix factorization, sparse representation, subspace clustering},
	pages = {63--66},
}

Downloads: 0