559 citations · 697 across the 13 of their papers we have counts for
16 papers
Conditioning of incoherent sub-dictionaries sampled from a coherent dictionary
Karin Schnass
Motivated by the desire to find a realistic and stable random model for -dimensional signals, that are sparse in a transform-based and thus often coherent frame, such as a wavel…
Convergence of alternating minimisation algorithms for dictionary learning
Simon Ruetz, Karin Schnass
In this paper we derive sufficient conditions for the convergence of two popular alternating minimisation algorithms for dictionary learning - the Method of Optimal Directions (MOD…
Bounds for matrices of inclusion probabilities in rejective sampling
Simon Ruetz, Karin Schnass
Motivated by a desire to model n-sparse signals more realistically, we study matrices of inclusion probabilities for conditional Poisson or rejective sampling in the non-asymptotic…
Submatrices with non-uniformly selected random supports and insights into sparse approximation
Simon Ruetz, Karin Schnass
In this paper we derive tail bounds on the norms of random submatrices with non-uniformly distributed supports. We apply these results to sparse approximation and conduct an analys…
Average performance of Orthogonal Matching Pursuit (OMP) for sparse approximation
Karin Schnass
We present a theoretical analysis of the average performance of OMP for sparse approximation. For signals that are generated from a dictionary with atoms and coherence and…
Compressed Dictionary Learning
Karin Schnass, Flavio Teixeira
In this paper we show that the computational complexity of the Iterative Thresholding and K-residual-Means (ITKrM) algorithm for dictionary learning can be significantly reduced by…