Results 11 to 20 of about 164,304 (297)

Partial Matrix Completion

Advances in Neural Information Processing Systems 36, 2023
The matrix completion problem aims to reconstruct a low-rank matrix based on a revealed set of possibly noisy entries. Prior works consider completing the entire matrix with generalization error guarantees. However, the completion accuracy can be drastically different over different entries.
Elad Hazan, Adam Tauman Kalai, Varun Kanade, Clara Mohri, Y. Jennifer Sun   +4 more
core   +7 more sources

Poisson matrix completion [PDF]

2015 IEEE International Symposium on Information Theory (ISIT), 2015
Submitted to IEEE for ...
Yang Cao 0013, Yao Xie 0002
openaire   +3 more sources

Conformalized matrix completion

Advances in Neural Information Processing Systems 36, 2023
Matrix completion aims to estimate missing entries in a data matrix, using the assumption of a low-complexity structure (e.g., low rank) so that imputation is possible. While many effective estimation algorithms exist in the literature, uncertainty quantification for this problem has proved to be challenging, and existing methods are extremely ...
Yu Gui, Rina Barber, Cong Ma 0001
openaire   +4 more sources

Matrix Completion With Noise [PDF]

Proceedings of the IEEE, 2010
11 pages, 4 figures, 1 ...
Candès, Emmanuel J., Plan, Yaniv
openaire   +4 more sources

Collective Matrix Completion

CoRR, 2018
Matrix completion aims to reconstruct a data matrix based on observations of a small number of its entries. Usually in matrix completion a single matrix is considered, which can be, for example, a rating matrix in recommendation system. However, in practical situations, data is often obtained from multiple sources which results in a collection of ...
Alaya, Mokhtar Z., Klopp, Olga
openaire   +6 more sources

Quaternion Matrix Factorization for Low-Rank Quaternion Matrix Completion

Mathematics, 2023
The main aim of this paper is to study quaternion matrix factorization for low-rank quaternion matrix completion and its applications in color image processing.
Jiang-Feng Chen, Qing-Wen Wang, Guang-Jing Song, Tao Li   +3 more
doaj   +1 more source

1-Bit matrix completion

Information and Inference, 2014
In this paper we develop a theory of matrix completion for the extreme case of noisy 1-bit observations. Instead of observing a subset of the real-valued entries of a matrix M, we obtain a small number of binary (1-bit) measurements generated according to a probability distribution determined by the real-valued entries of M. The central question we ask
Mark A. Davenport, Yaniv Plan, Ewout van den Berg, Mary Wootters   +3 more
openaire   +3 more sources

Matrix Completion with Queries [PDF]

Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015
Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data ...
Natali Ruchansky, Mark Crovella, Evimaria Terzi   +2 more
openaire   +2 more sources

Categorical matrix completion [PDF]

2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2015
We consider the problem of completing a matrix with categorical-valued entries from partial observations. This is achieved by extending the formulation and theory of one-bit matrix completion. We recover a low-rank matrix $X$ by maximizing the likelihood ratio with a constraint on the nuclear norm of $X$, and the observations are mapped from entries of
Yang Cao 0013, Yao Xie 0002
openaire   +2 more sources

Matrix Completion Based on Low-Rank and Local Features Applied to Images Recovery and Recommendation Systems

IEEE Access, 2022
Recent advances have shown that the challenging problem of matrix completion arises from real-world applications, such as image recovery, and recommendation systems.
Ying Zhang, Kai Xu, Songfeng Liang, Chen Zhao   +3 more
doaj   +1 more source