Title :
Identifiability bounds for bilinear inverse problems
Author :
Choudhary, Shobhit ; Mitra, U.
Author_Institution :
Univ. of Southern California, Los Angeles, CA, USA
Abstract :
A number of important inverse problems in signal processing, including blind deconvolution, dictionary learning and matrix factorization, are instances of bilinear inverse problems. This paper shows that bilinear inverse problems are identifiable with probability close to one for random inputs provided that the number of rank-2 matrices in the null space grows as o(mn) for key applications.
Keywords :
inverse problems; signal processing; bilinear inverse problems; blind deconvolution; dictionary learning; identifiability bounds; matrix factorization; signal processing; Convolution; Deconvolution; Manganese; Null space; Vectors; bilinear inverse problems; identifiability; rank-1 matrix recovery;
Conference_Titel :
Signals, Systems and Computers, 2013 Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
978-1-4799-2388-5
DOI :
10.1109/ACSSC.2013.6810585
