paper-with-me

Papers

Low-Rank Matrix Estimation From Rank-One Projections by Unlifted Convex Optimization

2020-04-06 · Sohail Bahmani, Kiryung Lee

We study an estimator with a convex formulation for recovery of low-rank matrices from rank-one projections. Using initial estimates of the factors of the target $d_1\times d_2$ matrix of rank-$r$, the estimator admits a practical subgradient method operating in a space of dimension $r(d_1+d_2)$. This property makes the estimator significantly more scalable than the convex estimators based on lifting and semidefinite programming. Furthermore, we present a streamlined analysis for exact recovery under the real Gaussian measurement model, as well as the partially derandomized measurement model by using the spherical $t$-design. We show that under both models the estimator succeeds, with high probability, if the number of measurements exceeds $r^2 (d_1+d_2)$ up to some logarithmic factors. This sample complexity improves on the existing results for nonconvex iterative algorithms.

📄 PDF Abstract BibTeX arXiv:2004.02718

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ROP: Matrix recovery via rank-one projections

2013-10-22 · T. Tony Cai, Anru Zhang

Estimation of low-rank matrices is of significant interest in a range of contemporary applications. In this paper, we introduce a rank-one projection model for low-rank matrix recovery and propose a constrained nuclear n…

Improved Algorithms for Matrix Recovery from Rank-One Projections

2017-05-21 · Mohammadreza Soltani, Chinmay Hegde

We consider the problem of estimation of a low-rank matrix from a limited number of noisy rank-one projections. In particular, we propose two fast, non-convex \emph{proper} algorithms for matrix recovery and support them…

Alternating projections gridless covariance-based estimation for DOA

2021-02-12 · Yongsung Park, Peter Gerstoft

We present a gridless sparse iterative covariance-based estimation method based on alternating projections for direction-of-arrival (DOA) estimation. The gridless DOA estimation is formulated in the reconstruction of Toe…

FIM-LoRA: Task-Informative Rank Allocation for LoRA via Calibration-Time Gradient-Variance Estimation

2026-05-16 · Ramakrishnan Sathyavageeswaran arxiv

Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: different layers contribute unequally to task adaptation. We address this wit…

Accelerated Alternating Projections for Robust Principal Component Analysis

2017-11-15 · HanQin Cai, Jian-Feng Cai, Ke Wei

We study robust PCA for the fully observed setting, which is about separating a low rank matrix $\boldsymbol{L}$ and a sparse matrix $\boldsymbol{S}$ from their sum $\boldsymbol{D}=\boldsymbol{L}+\boldsymbol{S}$. In this…

Computational Efficiency