English
Related papers

Related papers: Non-convex Robust PCA

200 papers

We propose greedy and local search algorithms for rank-constrained convex optimization, namely solving $\underset{\mathrm{rank}(A)\leq r^*}{\min}\, R(A)$ given a convex function $R:\mathbb{R}^{m\times n}\rightarrow \mathbb{R}$ and a…

Machine Learning · Computer Science 2021-01-18 Kyriakos Axiotis , Maxim Sviridenko

We propose a sparse regression method based on the non-concave penalized density power divergence loss function which is robust against infinitesimal contamination in very high dimensionality. Present methods of sparse and robust regression…

Methodology · Statistics 2021-05-18 Abhik Ghosh , Subhabrata Majumdar

We present novel techniques for analyzing the problem of low-rank matrix recovery. The methods are both considerably simpler and more general than previous approaches. It is shown that an unknown (n x n) matrix of rank r can be efficiently…

Information Theory · Computer Science 2011-03-22 David Gross

The low-rank matrix reconstruction (LRMR) approach is widely used in direction-of-arrival (DOA) estimation. As the rank norm penalty in an LRMR is NP-hard to compute, the nuclear norm (or the trace norm for a positive semidefinite (PSD)…

Information Theory · Computer Science 2017-12-07 Xiaohuan Wu , Wei-Ping Zhu , Jun Yan

This work studies low-rank approximation of a positive semidefinite matrix from partial entries via nonconvex optimization. We characterized how well local-minimum based low-rank factorization approximates a fixed positive semidefinite…

Optimization and Control · Mathematics 2019-04-08 Ji Chen , Xiaodong Li

This paper explores and analyzes two randomized designs for robust Principal Component Analysis (PCA) employing low-dimensional data sketching. In one design, a data sketch is constructed using random column sampling followed by low…

Machine Learning · Statistics 2017-03-21 Mostafa Rahmani , George Atia

We consider a problem of considerable practical interest: the recovery of a data matrix from a sampling of its entries. Suppose that we observe m entries selected uniformly at random from a matrix M. Can we complete the matrix and recover…

Information Theory · Computer Science 2008-05-30 Emmanuel J. Candes , Benjamin Recht

We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(\epsilon^{-3})$ to find $\epsilon$-approximate solution with one sample. That is, our…

Optimization and Control · Mathematics 2020-08-12 Andi Han , Junbin Gao

We study the computational cost of recovering a unit-norm sparse principal component $x \in \mathbb{R}^n$ planted in a random matrix, in either the Wigner or Wishart spiked model (observing either $W + \lambda xx^\top$ with $W$ drawn from…

Statistics Theory · Mathematics 2022-06-24 Yunzi Ding , Dmitriy Kunisky , Alexander S. Wein , Afonso S. Bandeira

The problem of recovering a low $n$-rank tensor is an extension of sparse recovery problem from the low dimensional space (matrix space) to the high dimensional space (tensor space) and has many applications in computer vision and graphics…

Optimization and Control · Mathematics 2014-04-09 Min Zhang , Lei Yang , Zheng-Hai Huang

We propose a robust principal component analysis (RPCA) framework to recover low-rank and sparse matrices from temporal observations. We develop an online version of the batch temporal algorithm in order to process larger datasets or…

Machine Learning · Statistics 2022-08-04 Hong-Lan Botterman , Julien Roussel , Thomas Morzadec , Ali Jabbari , Nicolas Brunel

Matrix low rank approximation including the classical PCA and the robust PCA (RPCA) method have been applied to solve the background modeling problem in video analysis. Recently, it has been demonstrated that a special weighted low rank…

Optimization and Control · Mathematics 2017-03-21 Aritra Dutta , Xin Li

We study the problem of sparse tensor principal component analysis: given a tensor $\pmb Y = \pmb W + \lambda x^{\otimes p}$ with $\pmb W \in \otimes^p\mathbb{R}^n$ having i.i.d. Gaussian entries, the goal is to recover the $k$-sparse unit…

Machine Learning · Computer Science 2021-11-03 Davin Choo , Tommaso d'Orsi

We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general…

Machine Learning · Statistics 2016-10-18 Lingxiao Wang , Xiao Zhang , Quanquan Gu

We improve the current best running time value to invert sparse matrices over finite fields, lowering it to an expected $O\big(n^{2.2131}\big)$ time for the current values of fast rectangular matrix multiplication. We achieve the same…

Data Structures and Algorithms · Computer Science 2022-12-13 Sílvia Casacuberta , Rasmus Kyng

In this paper, we consider the matrix recovery from rank-one projection measurements proposed in [Cai and Zhang, Ann. Statist., 43(2015), 102-138], via nonconvex minimization. We establish a sufficient identifiability condition, which can…

Information Theory · Computer Science 2018-06-29 Peng Li , Wengu Chen

Sparse principal component analysis (PCA) and sparse canonical correlation analysis (CCA) are two essential techniques from high-dimensional statistics and machine learning for analyzing large-scale data. Both problems can be formulated as…

Machine Learning · Statistics 2019-03-28 Shixiang Chen , Shiqian Ma , Lingzhou Xue , Hui Zou

Over the past years Robust PCA has been established as a standard tool for reliable low-rank approximation of matrices in the presence of outliers. Recently, the Robust PCA approach via nuclear norm minimization has been extended to…

Machine Learning · Statistics 2015-06-15 Clemens Hage , Martin Kleinsteuber

We consider the problem of robust matrix completion, which aims to recover a low rank matrix $L_*$ and a sparse matrix $S_*$ from incomplete observations of their sum $M=L_*+S_*\in\mathbb{R}^{m\times n}$. Algorithmically, the robust matrix…

Machine Learning · Statistics 2020-03-25 Yunfeng Cai , Ping Li

Given a sample covariance matrix, we examine the problem of maximizing the variance explained by a linear combination of the input variables while constraining the number of nonzero coefficients in this combination. This is known as sparse…

Optimization and Control · Mathematics 2010-12-24 Youwei Zhang , Alexandre d'Aspremont , Laurent El Ghaoui