Norms of Random Submatrices and Sparse Approximation

86 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals (2009, background): “2 of [65] combined with a standard decoupling argument (e.”
On the Local Correctness of L^1 Minimization for Dictionary Learning (2011, methodology): “In particular, several steps are quite similar to manipulations in the proof of Proposition 2.1 of [Tro08], and are repeated here for completeness.”
Compressive Sensing by Random Convolution (2009, methodology): “where the rk are rows in the matrix H ; we will call () the cumulative coherence (this quantity was also used in [ 37 ]).”
Contextual Bandits with Latent Confounders: An NMF Approach (2016, background): “Remark: In prior works [6, 11, 37, 36, 10] the statistical RIP property was established by relating it to the incoherence parameter μ of a matrix B which is defined as μ (B) = max i 6=j |bT”
An Introduction to Matrix Concentration Inequalities (2015, unknown): “When analyzing methods for identifying the sparse set of coefficients, we must study the behavior of a random column submatrix drawn from the model matrix [177, 176].”
Near-ideal model selection by ℓ1 minimization (2008, background): “15) can be derived from the last equation in Section 4 of [27].”