paper-with-me

홈 › Papers

A note on the statistical view of matrix completion

2016-05-10 · Tianxi Li

A very simple interpretation of matrix completion problem is introduced based on statistical models. Combined with the well-known results from missing data analysis, such interpretation indicates that matrix completion is still a valid and principled estimation procedure even without the missing completely at random (MCAR) assumption, which almost all of the current theoretical studies of matrix completion assume.

📄 PDF Abstract BibTeX arXiv:1605.03040

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completionvalid

Similar Papers 제목 키워드 기반

Matrix completion with deterministic pattern - a geometric perspective

2018-01-31 · Alexander Shapiro, Yao Xie, Rui Zhang

We consider the matrix completion problem with a deterministic pattern of observed entries. In this setting, we aim to answer the question: under what condition there will be (at least locally) unique solution to the mat…

Matrix Completion

Information-theoretic Bounds on Matrix Completion under Union of Subspaces Model

2015-08-14 · Vaneet Aggarwal, Shuchin Aeron

In this short note we extend some of the recent results on matrix completion under the assumption that the columns of the matrix can be grouped (clustered) into subspaces (not necessarily disjoint or independent). This m…

ClusteringMatrix Completion

Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions

2017-09-25 · Congcong Jin, Jihua Zhu, Yaochen Li, Shanmin Pang 외

Recently, the low rank and sparse (LRS) matrix decomposition has been introduced as an effective mean to solve the multi-view registration. It views each available relative motion as a block element to reconstruct one ma…

Notes on Low-rank Matrix Factorization

2015-06-30 · Yuan Lu, Jie Yang

Low-rank matrix factorization (MF) is an important technique in data science. The key idea of MF is that there exists latent structures in the data, by uncovering which we could obtain a compressed representation of the …

ClusteringDimensionality ReductionMatrix Completion

Always Valid Risk Monitoring for Online Matrix Completion

2022-11-18 · Chi-Hua Wang, Wenjie Li

Always-valid concentration inequalities are increasingly used as performance measures for online statistical learning, notably in the learning of generative models and supervised learning. Such inequality advances the on…

Matrix Completionvalid