Command Palette
Search for a command to run...
Abhimanyu Das Weihao Kong Andrew Leach Shaan Mathur Rajat Sen Rose Yu
Abstract
Recent work has shown that simple linear models can outperform several Transformer based approaches in long term time-series forecasting. Motivated by this, we propose a Multi-layer Perceptron (MLP) based encoder-decoder model, Time-series Dense Encoder (TiDE), for long-term time-series forecasting that enjoys the simplicity and speed of linear models while also being able to handle covariates and non-linear dependencies. Theoretically, we prove that the simplest linear analogue of our model can achieve near optimal error rate for linear dynamical systems (LDS) under some assumptions. Empirically, we show that our method can match or outperform prior approaches on popular long-term time-series forecasting benchmarks while being 5-10x faster than the best Transformer based model.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| time-series-forecasting-on-etth1-192-1 | TiDE | MAE: 0.422 MSE: 0.412 |
| time-series-forecasting-on-etth1-336-1 | TiDE | MAE: 0.433 MSE: 0.435 |
| time-series-forecasting-on-etth1-720-1 | TiDE | MAE: 0.465 MSE: 0.454 |
| time-series-forecasting-on-etth1-96-1 | TiDE | MAE: 0.398 MSE: 0.375 |
| time-series-forecasting-on-etth2-192-1 | TiDE | MAE: 0.38 MSE: 0.332 |
| time-series-forecasting-on-etth2-336-1 | TiDE | MAE: 0.407 MSE: 0.36 |
| time-series-forecasting-on-etth2-720-1 | TiDE | MAE: 0.451 MSE: 0.419 |
| time-series-forecasting-on-etth2-96-1 | TiDE | MAE: 0.336 MSE: 0.27 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.