Hard-thresholding Operator on A Covariance MatrixBinhuan Wang
A family of conjugate gradient iterative hard thresholding (CGIHT) algorithms was proposed in Blanchard et al. (2015). It was also proved that a restarted version of CGIHT converges linearly to X under the RIP assumption of A. The performance guarantee of IHT for matrix completion is recently...
We consider recovery of low-rank matrices from noisy data by hard thresholding of singular values, where singular values below a prescribed threshold \lambda are set to 0. We study the asymptotic MSE in a framework where the matrix size is large compared to the rank of the matrix to be rec...
Minimax risk of matrix denoising by singular value thresholding An unknown m by n matrix X-0 is to be estimated from noisy measurements Y = X-0 + Z, where the noise matrix Z has i.i.d. Gaussian entries. A popular matrix... D Donoho,M Gavish - 《Annals of Statistics》 被引量: 89...
We propose a fast Newton hard thresholding pursuit algorithm for sparsity constrained nonconvex optimization. Our proposed algorithm reduces the per-iterat... CQ Gu - 《Sigkdd Explorations》 被引量: 0发表: 2017年 Sparsistency and rates of convergence in large covariance matrix estimation On the ...
值得一提的是,IHT在文献【2】中提出时并不叫Iterative Hard Thresholding,而是M-Sparse Algorithm,如下图所示: 该算法是为了求解M-稀疏问题(M-sparse problem)式(3.1)而提出的,经过一番推导得到了迭代公式式(3.2),其中HM(·)的含义参见式(3.3)。
We consider the problem of low rank matrix recovery in a stochastically noisy high dimensional setting. We propose a new estimator for the low rank matrix, based on the iterative hard thresholding method, and that is computationally efficient and simple. We prove that our estimator is efficient ...
In this work, we study a simple hard-thresholding algorithm called \alg which, under mild conditions on $X$, can recover $\bto$ exactly even if $\b$ corrupts the response variables in an \emph{adversarial} manner, i.e. both the support and entries of $\b$ are selected adversarially ...
摘要: Propose the expander normalized heavy ball hard thresholding algorithm.Convergence rate and accuracy of proposed algorithm are provided.Our method achieves good numerical performance, especially in the presence of outliers.关键词: Combinatorial compressed sensing Sparse signal recovery Heavy ball method...
A novel algorithm for the recovery of low-rank matrices acquired via compressive linear measurements is proposed and analyzed. The algorithm, a variation on the iterative hard thresholding algorithm for low-rank recovery, is designed to succeed in situations where the standard rank-restricted isometry...