Saved in:
Bibliographic Details
Main Authors: Das, Abhimanyu, Kong, Weihao, Leach, Andrew, Mathur, Shaan, Sen, Rajat, Yu, Rose
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2304.08424
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914741044117504
author Das, Abhimanyu
Kong, Weihao
Leach, Andrew
Mathur, Shaan
Sen, Rajat
Yu, Rose
author_facet Das, Abhimanyu
Kong, Weihao
Leach, Andrew
Mathur, Shaan
Sen, Rajat
Yu, Rose
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2304_08424
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Long-term Forecasting with TiDE: Time-series Dense Encoder
Das, Abhimanyu
Kong, Weihao
Leach, Andrew
Mathur, Shaan
Sen, Rajat
Yu, Rose
Machine Learning
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.
title Long-term Forecasting with TiDE: Time-series Dense Encoder
topic Machine Learning
url https://arxiv.org/abs/2304.08424