Online adaptive forecasting of a locally stationary time varying autoregressive process
نویسنده
چکیده
In this work, we study the problem of online adaptive forecasting for locally stationary Time Varying Autoregressive processes (TVAR). The Normalized Mean Least Squares algorithm (NMLS) is an online stochastic gradient method which has been shown to perform efficiently, provided that the gradient step size is well chosen. This choice highly depends on the smoothness exponent of the evolving parameters. In this contribution, we show that a sequential aggregation of several NLMS estimators at various gradient step sizes is able to adapt to an unknown smoothness, resulting in an online adaptive predictor.
منابع مشابه
Aggregation of Predictors for Non Stationary Sub-linear Processes and Online Adaptive Forecasting of Time Varying Autoregressive Processes
In this work, we study the problem of aggregating a finite number of predictors for non stationary sub-linear processes. We provide oracle inequalities relying essentially on three ingredients: 1) a uniform bound of the `1 norm of the time-varying sub-linear coefficients, 2) a Lipschitz assumption on the predictors and 3) moment conditions on the noise appearing in the linear representation. Tw...
متن کاملSome New Methods for Prediction of Time Series by Wavelets
Extended Abstract. Forecasting is one of the most important purposes of time series analysis. For many years, classical methods were used for this aim. But these methods do not give good performance results for real time series due to non-linearity and non-stationarity of these data sets. On one hand, most of real world time series data display a time-varying second order structure. On th...
متن کاملA new adaptive exponential smoothing method for non-stationary time series with level shifts
Simple exponential smoothing (SES) methods are the most commonly used methods in forecasting and time series analysis. However, they are generally insensitive to non-stationary structural events such as level shifts, ramp shifts, and spikes or impulses. Similar to that of outliers in stationary time series, these non-stationary events will lead to increased level of errors in the forecasting pr...
متن کاملAn Improved Automatic EEG Signal Segmentation Method based on Generalized Likelihood Ratio
It is often needed to label electroencephalogram (EEG) signals by segments of similar characteristics that are particularly meaningful to clinicians and for assessment by neurophysiologists. Within each segment, the signals are considered statistically stationary, usually with similar characteristics such as amplitude and/or frequency. In order to detect the segments boundaries of a signal, we ...
متن کاملComparing Time-Varying autoregressive Structures of Locally Stationary Processes
In this paper a novel statistical test is introduced to compare two locally stationary time series. The proposed approach is a Wald test considering time-varying autoregressive modelling and function projections in adequate spaces. The covariance structure of the innovations may be also time-varying. In order to obtain function estimators for the time-varying autoregressive parameters, we consi...
متن کامل