AI Paper Atlas

Research map / Time series / Causal and generative time series

Conformal Prediction for Time Series with Modern Hopfield Networks

Andreas Auer, Martin Gauch, Daniel Klotz, Sepp Hochreiter

NeurIPS 2023 · Time series › Causal and generative time series · approach: Probabilistic and conformal forecasting · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use HopCPT's learned MHN regime retrieval instead of recency-based SPCI weightingconformal prediction for time series · Solar 3Y (LightGBM)PI-Width: 102.2 -> 37.7Improved
use HopCPT instead of SPCI on LSTM predictions for Air 10 PMconformal prediction · Air 10 PM (LSTM)Winkler score: 1.21 -> 1.33Hurt
use HopCPT instead of standard split CP under strong error trendconformal prediction · Sap flow (Ridge)coverage gap: -0.358 -> -0.025Improved
use HopCPT instead of SPCI on streamflow dataconformal prediction · Streamflow (LSTM)PI-Width: 1.58 -> 1.39Improved
increase dataset size (more data for HopCPT)HopCPT · Solar datasets (1Y, 3Y)PI-Width leadImproved
replace learned MHN similarity with kNN retrieval (ablation)HopCPT · smallest Solar datasetefficiencyImproved
use HopCPT vs EnbPI regarding coverageconformal prediction · Solar 3Y (Ridge)coverage gap: -0.074 -> 0.040Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy