Tight risk bound for high dimensional time series completion
DOI10.1214/22-EJS2015zbMath1493.62545arXiv2102.08178OpenAlexW3131747410MaRDI QIDQ2137821
Nicolas Marie, Pierre Alquier, Amélie Rosier
Publication date: 11 May 2022
Published in: Electronic Journal of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2102.08178
matrix completionmixingmatrix factorizationconcentration inequalitieshigh-dimensional time seriesmultivariate time series analysis
Inference from stochastic processes and prediction (62M20) Factor analysis and principal components; correspondence analysis (62H25) Estimation in multivariate analysis (62H12) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Random matrices (probabilistic aspects) (60B20) Ergodicity, mixing, rates of mixing (37A25)
Cites Work
- Unnamed Item
- Unnamed Item
- Factor modeling for high-dimensional time series: inference for the number of factors
- Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
- Robust matrix completion
- Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
- Mixing: Properties and examples
- 1-bit matrix completion: PAC-Bayesian analysis of a variational approximation
- Adaptive confidence sets for matrix completion
- Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
- Matrix factorization for multivariate time series analysis
- High-dimensional VAR with low-rank transition
- Concentration of tempered posteriors and of their variational approximations
- A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
- Noisy low-rank matrix completion with general sampling distribution
- Factor models in high-dimensional time series: A time-domain approach
- Exact matrix completion via convex optimization
- Forecasting in dynamic factor models using Bayesian model averaging
- Estimation of latent factors for high-dimensional time series
- Low Rank and Structured Modeling of High-Dimensional Vector Autoregressions
- Invariant Inference and Efficient Computation in the Static Factor Model
- Minimal penalties and the slope heuristics: a survey
- Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
- Recovering Low-Rank Matrices From Few Coefficients in Any Basis
- Matrix Completion From a Few Entries
- The Power of Convex Relaxation: Near-Optimal Matrix Completion
- Learning the parts of objects by non-negative matrix factorization
- Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
- Prediction of time series by statistical learning: general losses and fast rates
- Introduction to nonparametric estimation
This page was built for publication: Tight risk bound for high dimensional time series completion
