Prediction of time series by statistical learning: general losses and fast rates

DOI10.2478/demo-2013-0004MaRDI QIDQ5417591

Olivier Wintenberger, Xiaoyin Li, Pierre Alquier

Publication date: 21 May 2014

Published in: Dependence Modeling (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1211.1847

zbMATH Keywords

mixing; time series forecasting; statistical learning theory; weak dependence; oracle inequalities; fast rates; GDP forecasting; PACBayesian bounds

Mathematics Subject Classification ID

62P20: Applications of statistics to economics

62M20: Inference from stochastic processes and prediction

62M10: Time series, auto-correlation, regression, etc. in statistics (GARCH)

68Q32: Computational learning theory

68T05: Learning and adaptive systems in artificial intelligence

60G25: Prediction theory (aspects of stochastic processes)

Related Items

User-friendly Introduction to PAC-Bayes Bounds, Optimal learning with Bernstein Online Aggregation, Simpler PAC-Bayesian bounds for hostile data, Tight risk bound for high dimensional time series completion, Deviation inequalities for stochastic approximation by averaging, Exponential inequalities for nonstationary Markov chains, Discrepancy-based theory and algorithms for forecasting non-stationary time series, High-dimensional VAR with low-rank transition, Generalization bounds for non-stationary mixing processes, On some recent advances on high dimensional Bayesian statistics, Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers

Uses Software

• R

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Model selection for weakly dependent time series forecasting
• Deviation inequalities for sums of weakly dependent time series
• Markov chains and stochastic stability
• PAC-Bayesian bounds for randomized empirical risk minimizers
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Weakly dependent chains with infinite memory
• Learning by mirror averaging
• Learning from dependent observations
• Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
• Time series: Theory and methods
• Mixing: Properties and examples
• The weighted majority algorithm
• Nonparametric time series prediction through adaptive model selection
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
• Sharp oracle inequalities for aggregation of affine estimators
• PAC-Bayesian bounds for sparse regression estimation with exponential weights
• The generalization performance of ERM algorithm with strongly mixing observations
• Fast learning rates in statistical inference through aggregation
• Learning rates of regularized regression for exponentially strongly mixing sequence
• \(\ell_1\)-penalized quantile regression in high-dimensional sparse models
• Recursive aggregation of estimators by the mirror descent algorithm with averaging
• Fast learning from \(\alpha\)-mixing observations
• Aggregation for Gaussian regression
• Weak dependence. With examples and applications.
• Generalization and Robustness of Batched Weighted Average Algorithm with V-Geometrically Ergodic Markov Data
• The Generalization Ability of Online Algorithms for Dependent Data
• PAC-Bayesian Inequalities for Martingales
• Mixing properties of harris chains and autoregressive processes
• Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation
• Asymptotic evaluation of certain Markov process expectations for large time—III
• Regression Quantiles
• Memory-universal prediction of stationary random processes
• Inégalités de Hoeffding pour les fonctions lipschitziennes de suites dépendantes
• Ergodic Mirror Descent
• GARCH Models
• Sequential Quantile Prediction of Time Series
• Sparsity regret bounds for individual sequences in online linear regression
• Prediction, Learning, and Games
• Some Limit Theorems for Stationary Processes
• Gaussian model selection