Conformal Prediction for Time Series with Modern Hopfield Networks

Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter
3/22/2023
cs.LGcs.AIstat.ML

No official code found. Best implementation: ml-jku/HopCPT (85 stars, MIT, last commit 2025-05-28).

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.

View on arXivView PDF

Code Implementations(1)

ml-jku/HopCPTCommunity100%
MIT

Conformal Prediction for Time Series with Modern Hopfield Networks

8513Python, Jupyter NotebookMar 22, 20231 years agoMIT

Similar Papers

Conformal Prediction for Time-series Forecasting with Change Points

90% match1 repo272025

Flow-based Conformal Prediction for Multi-dimensional Time Series

88% match2025

Conformal time series decomposition with component-wise exchangeability

88% match1 repo22024

ResCP: Reservoir Conformal Prediction for Time Series Forecasting

87% match2025

Relational Conformal Prediction for Correlated Time Series

86% match1 repo182026

A Gentle Introduction to Conformal Time Series Forecasting

86% match2025

Cite this paper

@article{auer2023conformal,
  title  = {Conformal Prediction for Time Series with Modern Hopfield Networks},
  author = {Andreas Auer and Martin Gauch and Daniel Klotz and Sepp Hochreiter},
  year   = {2023},
  eprint = {2303.12783},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.12783v2},
  journal = {NEURIPS 2023 2023}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.12783.svg)](https://codeofpaper.com/paper/2303.12783)

Discussion