Matrix completion and extrapolation via kernel regression

08/01/2018
by   Pere Giménez-Febrer, et al.
0

Matrix completion and extrapolation (MCEX) are dealt with here over reproducing kernel Hilbert spaces (RKHSs) in order to account for prior information present in the available data. Aiming at a faster and low-complexity solver, the task is formulated as a kernel ridge regression. The resultant MCEX algorithm can also afford online implementation, while the class of kernel functions also encompasses several existing approaches to MC with prior information. Numerical tests on synthetic and real datasets show that the novel approach performs faster than widespread methods such as alternating least squares (ALS) or stochastic gradient descent (SGD), and that the recovery error is reduced, especially when dealing with noisy data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/20/2019

Generalization error bounds for kernel matrix completion and extrapolation

Prior information can be incorporated in matrix completion to improve es...
research
10/21/2019

Fast Exact Matrix Completion: A Unifying Optimization Framework

We consider the problem of matrix completion of rank k on an n× m matrix...
research
05/26/2016

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent

Matrix completion, where we wish to recover a low rank matrix by observi...
research
07/12/2022

Optimal tuning-free convex relaxation for noisy matrix completion

This paper is concerned with noisy matrix completion–the problem of reco...
research
01/18/2019

Nonconvex Rectangular Matrix Completion via Gradient Descent without ℓ_2,∞ Regularization

The analysis of nonconvex matrix completion has recently attracted much ...
research
08/24/2022

Accelerating SGD for Highly Ill-Conditioned Huge-Scale Online Matrix Completion

The matrix completion problem seeks to recover a d× d ground truth matri...
research
09/08/2021

Matrix Completion of World Trade

This work applies Matrix Completion (MC) – a class of machine-learning m...

Please sign up or login with your details

Forgot password? Click here to reset