SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters

arXiv:2405.00946v1 Announce Type: new
Abstract: This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features …

arxiv cs.lg forecasting long-term modeling parameters series time series time series forecasting type