Generalization Error Bounds for Kernel Matrix Completion and Extrapolation

Prior information can be incorporated in matrix completion to improve estimation accuracy and extrapolate the missing entries. Reproducing kernel Hilbert spaces provide tools to leverage the said prior information, and derive more reliable algorithms. This paper analyzes the generalization error of such approaches, and presents numerical tests confirming the theoretical results.

[1]  Prateek Jain,et al.  Low-rank matrix completion using alternating minimization , 2012, STOC '13.

[2]  Lei Yao,et al.  A DCT Regularized Matrix Completion Algorithm for Energy Efficient Data Gathering in Wireless Sensor Networks , 2015, Int. J. Distributed Sens. Networks.

[3]  Shiqian Ma,et al.  Fixed point and Bregman iterative methods for matrix rank minimization , 2009, Math. Program..

[4]  Guillermo Sapiro,et al.  Kernelized Probabilistic Matrix Factorization: Exploiting Graphs and Side Information , 2012, SDM.

[5]  Inderjit S. Dhillon,et al.  Provable Inductive Matrix Completion , 2013, ArXiv.

[6]  Gonzalo Mateos,et al.  Rank Regularization and Bayesian Inference for Tensor Completion and Extrapolation , 2013, IEEE Transactions on Signal Processing.

[7]  Georgios B. Giannakis,et al.  Matrix Completion and Extrapolation via Kernel Regression , 2018, IEEE Transactions on Signal Processing.

[8]  Alba Pagès-Zamora,et al.  Matrix completion of noisy graph signals via proximal gradient minimization , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[10]  Nathan Srebro,et al.  Concentration-Based Guarantees for Low-Rank Matrix Reconstruction , 2011, COLT.

[11]  Jiawei Han,et al.  Towards Active Learning on Graphs: An Error Bound Minimization Approach , 2012, 2012 IEEE 12th International Conference on Data Mining.

[12]  Ohad Shamir,et al.  Matrix completion with the trace norm: learning, bounding, and transducing , 2014, J. Mach. Learn. Res..

[13]  Yoan Shin,et al.  Matrix Completion Optimization for Localization in Wireless Sensor Networks for Intelligent IoT , 2016, Sensors.

[14]  Ran El-Yaniv,et al.  Transductive Rademacher Complexity and Its Applications , 2007, COLT.

[15]  Pradeep Ravikumar,et al.  Collaborative Filtering with Graph Information: Consistency and Scalable Methods , 2015, NIPS.

[16]  Adi Shraibman,et al.  Rank, Trace-Norm and Max-Norm , 2005, COLT.

[17]  Qiang Ye,et al.  STCDG: An Efficient Data Gathering Algorithm Based on Matrix Completion for Wireless Sensor Networks , 2013, IEEE Transactions on Wireless Communications.

[18]  Angshul Majumdar,et al.  Matrix completion incorporating auxiliary information for recommender system design , 2015, Expert Syst. Appl..

[19]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[20]  Georgios B. Giannakis,et al.  Nonparametric Basis Pursuit via Sparse Kernel-Based Learning: A Unifying View with Advances in Blind Methods , 2013, IEEE Signal Processing Magazine.

[21]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[22]  Emmanuel J. Candès,et al.  Matrix Completion With Noise , 2009, Proceedings of the IEEE.

[23]  Yehuda Koren,et al.  Matrix Factorization Techniques for Recommender Systems , 2009, Computer.

[24]  Ruoyu Sun.  Matrix Completion via Nonconvex Factorization: Algorithms and Theory , 2015 .

[25]  José M. F. Moura,et al.  Signal Recovery on Graphs: Variation Minimization , 2014, IEEE Transactions on Signal Processing.

[26]  Zuowei Shen,et al.  Robust video denoising using low rank matrix completion , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[27]  Xavier Bresson,et al.  Matrix Completion on Graphs , 2014, NIPS 2014.

[28]  Francis R. Bach,et al.  Low-rank matrix factorization with attributes , 2006, ArXiv.