Deep Double Descent for Time Series Forecasting: Avoiding Undertrained Models

no code implementations • 2 Nov 2023 • Valentino Assandri, Sam Heshmati, Burhaneddin Yaman, Anton Iakovlev, Ariel Emiliano Repetur

While existing time series literature primarily focuses on model architecture modifications and data augmentation techniques, this paper explores the training schema of deep learning models for time series; how models are trained regardless of their architecture.

Data Augmentation Time Series +1