New conformal prediction methods for time series using deep learning

This paper introduces three novel approaches to conformal prediction for time series data, addressing the challenge of violated exchangeability assumptions inherent in time series. The proposed methods leverage deep sequence models, including Recurrent Neural Networks and Transformers, to achieve asymptotic conditional coverage guarantees. Experimental results on real-world datasets demonstrate the effectiveness of these deep learning-enhanced conformal prediction techniques. AI

IMPACT Enhances uncertainty quantification for time series predictions, potentially improving reliability in applications like financial forecasting and climate modeling.

RANK_REASON The cluster contains a research paper published on arXiv detailing new methods for conformal prediction in time series using deep learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Conditional Quantile Function Estimation
• Conditional quantile regression models of melanoma tumor growth curves for assessing treatment effect in small sample studies
• Conformal prediction
• deep sequence models
• Localized Conformal Prediction
• Recurrent Neural Networks
• time series
• Transformers

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →