Tight risk bound for high dimensional time series completion
From MaRDI portal
matrix factorizationhigh-dimensional time seriesmatrix completionmixingconcentration inequalitiesmultivariate time series analysis
Factor analysis and principal components; correspondence analysis (62H25) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Estimation in multivariate analysis (62H12) Inference from stochastic processes and prediction (62M20) Random matrices (probabilistic aspects) (60B20) Ergodicity, mixing, rates of mixing (37A25)
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.
Recommendations
Cites work
- 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation
- A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
- Adaptive confidence sets for matrix completion
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Concentration inequalities. A nonasymptotic theory of independence
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Concentration of tempered posteriors and of their variational approximations
- Estimation of latent factors for high-dimensional time series
- Exact matrix completion via convex optimization
- Factor modeling for high-dimensional time series: inference for the number of factors
- Factor models in high-dimensional time series: A time-domain approach
- Forecasting in dynamic factor models using Bayesian model averaging
- High-dimensional VAR with low-rank transition
- Introduction to nonparametric estimation
- Invariant inference and efficient computation in the static factor model
- Learning the parts of objects by non-negative matrix factorization
- Low Rank and Structured Modeling of High-Dimensional Vector Autoregressions
- Matrix Completion From a Few Entries
- Matrix completion from noisy entries
- Matrix factorization for multivariate time series analysis
- Minimal penalties and the slope heuristics: a survey
- Mixing: Properties and examples
- Noisy low-rank matrix completion with general sampling distribution
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Prediction of time series by statistical learning: general losses and fast rates
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Restricted strong convexity and weighted matrix completion: optimal bounds with noise
- Robust matrix completion
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
This page was built for publication: Tight risk bound for high dimensional time series completion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2137821)
