Conformal Prediction for Time Series with Modern Hopfield Networks

Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter

Keywords: time series, uncertainty, prediction interval, conformal prediction, modern hopfield networks

TL;DR: We propose HopCPT, a novel uncertainty estimation approach designed for time serie which is based on conformal prediction and uses continuous Modern Hopfield Networks for similarity-based sample reweighting.

Abstract: To quantify uncertainty, conformal prediction methods are gaining continuously more interest and have already been successfully applied to various domains. However, they are difficult to apply to time series as the autocorrelative structure of time series violates basic assumptions required by conformal prediction. We propose HopCPT, a novel conformal prediction approach for time series that not only copes with temporal structures but leverages them. We show that our approach is theoretically well justified for time series where temporal dependencies are present. In experiments, we demonstrate that our new approach outperforms state-of-the-art conformal prediction methods on multiple real-world time series datasets from four different domains.

Submission Number: 6410