Tight Risk Bound for High Dimensional Time Series Completion - Archive ouverte HAL Access content directly
Journal Articles Electronic Journal of Statistics Year : 2022

Tight Risk Bound for High Dimensional Time Series Completion

Abstract

Initially designed for independent datas, low-rank matrix completion was successfully applied in many domains to the reconstruction of partially observed high-dimensional time series. However, there is a lack of theory to support the application of these methods to dependent datas. In this paper, we propose a general model for multivariate, partially observed time series. We show that the least-square method with a rank penalty leads to reconstruction error of the same order as for independent datas. Moreover, when the time series has some additional properties such as periodicity or smoothness, the rate can actually be faster than in the independent case.
Fichier principal
Vignette du fichier
Tight_Risk_Bound_For_High_Dimensional_Time_Series_Completion.pdf (581.22 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03142254 , version 1 (15-02-2021)
hal-03142254 , version 2 (26-05-2021)
hal-03142254 , version 3 (11-03-2022)

Identifiers

Cite

Pierre Alquier, Nicolas Marie, Amélie Rosier. Tight Risk Bound for High Dimensional Time Series Completion. Electronic Journal of Statistics , 2022, 16 (1), pp.3001-3035. ⟨10.1214/22-EJS2015⟩. ⟨hal-03142254v3⟩
147 View
128 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More