Generalisation in fully-connected neural networks for time series forecasting
In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being i.i.d. samples from some data-generating distribution. We us...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | In this paper we study the generalization capabilities of fully-connected
neural networks trained in the context of time series forecasting. Time series
do not satisfy the typical assumption in statistical learning theory of the
data being i.i.d. samples from some data-generating distribution. We use the
input and weight Hessians, that is the smoothness of the learned function with
respect to the input and the width of the minimum in weight space, to quantify
a network's ability to generalize to unseen data. While such generalization
metrics have been studied extensively in the i.i.d. setting of for example
image recognition, here we empirically validate their use in the task of time
series forecasting. Furthermore we discuss how one can control the
generalization capability of the network by means of the training process using
the learning rate, batch size and the number of training iterations as
controls. Using these hyperparameters one can efficiently control the
complexity of the output function without imposing explicit constraints. |
---|---|
DOI: | 10.48550/arxiv.1902.05312 |