HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Contributor : Nicolas Marie Connect in order to contact the contributor
Submitted on : Wednesday, May 26, 2021 - 1:07:57 PM
Last modification on : Tuesday, March 15, 2022 - 3:34:53 AM


Files produced by the author(s)


  • HAL Id : hal-03142254, version 2


Pierre Alquier, Nicolas Marie, Amélie Rosier. Tight Risk Bound for High Dimensional Time Series Completion. 2021. ⟨hal-03142254v2⟩



Record views


Files downloads