Convex optimization for matrix completion with application to forecasting - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Convex optimization for matrix completion with application to forecasting

Résumé

We consider convex relaxations for the low-rank matrix completion problem with specific application to forecasting time series and consider how close the solution of the convex relaxed low-rank matrix completion problem is to the original global optimization problem. This is a fashionable approach in the statistics of big data, difficult non-convex optimization problems are ‘convexified’ to make them tractable. The question then is: how close is the solution of the convex optimization problem to the non-convex one (which is the one we really want to solve)? We consider a matrix completion problem for Hankel matrices and investigate some cases when the proposed approach can work through theoretical and empirical results.

Dates et versions

hal-02402057 , version 1 (10-12-2019)

Identifiants

Citer

Jonathan Gillard, Konstantin Usevich. Convex optimization for matrix completion with application to forecasting. 14th International Global Optimization Workshop, LeGO 2018, Sep 2018, Leiden, Netherlands. pp.020042, ⟨10.1063/1.5090009⟩. ⟨hal-02402057⟩
30 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More