Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting

arXiv:2405.03199v1 Announce Type: new
Abstract: Deep learning methods have been exerting their strengths in long-term time series forecasting. However, they often struggle to strike a balance between expressive power and computational efficiency. Here, we propose the Coarsened Perceptron Network (CP-Net), a novel architecture that efficiently enhances the predictive capability of MLPs while maintains a linear computational complexity. It utilizes a coarsening strategy as the backbone that leverages two-stage convolution-based sampling blocks. Based purely on convolution, they provide the functionality of …

abstract architecture arxiv balance boosting capability computational cs.lg deep learning efficiency forecasting however long-term network novel perceptron power predictive series strategy strike struggle time series time series forecasting type