WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting

10/25/2022
by   Youngin Cho, et al.
0

Time series forecasting has become a critical task due to its high practicality in real-world applications such as traffic, energy consumption, economics and finance, and disease analysis. Recent deep-learning-based approaches have shown remarkable success in time series forecasting. Nonetheless, due to the dynamics of time series data, deep networks still suffer from unstable training and overfitting. Inconsistent patterns appearing in real-world data lead the model to be biased to a particular pattern, thus limiting the generalization. In this work, we introduce the dynamic error bounds on training loss to address the overfitting issue in time series forecasting. Consequently, we propose a regularization method called WaveBound which estimates the adequate error bounds of training loss for each time step and feature at each iteration. By allowing the model to focus less on unpredictable data, WaveBound stabilizes the training process, thus significantly improving generalization. With the extensive experiments, we show that WaveBound consistently improves upon the existing models in large margins, including the state-of-the-art model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/06/2020

Improving the Accuracy of Global Forecasting Models using Time Series Data Augmentation

Forecasting models that are trained across sets of many time series, kno...
research
01/08/2023

Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

Time series forecasting has been a widely explored task of great importa...
research
08/02/2023

Enhancing Representation Learning for Periodic Time Series with Floss: A Frequency Domain Regularization Approach

Time series analysis is a fundamental task in various application domain...
research
06/03/2021

Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems

The demand of probabilistic time series forecasting has been recently ra...
research
01/17/2023

Enhancing Deep Traffic Forecasting Models with Dynamic Regression

A common assumption in deep learning-based multivariate and multistep tr...
research
10/17/2022

Flipped Classroom: Effective Teaching for Time Series Forecasting

Sequence-to-sequence models based on LSTM and GRU are a most popular cho...
research
11/22/2022

Time Series Forecasting with Hypernetworks Generating Parameters in Advance

Forecasting future outcomes from recent time series data is not easy, es...

Please sign up or login with your details

Forgot password? Click here to reset