AI Paper Atlas

Research map / Time series / Causal and generative time series

Probabilistic Forecasting: A Level-Set Approach

Hilaf Hasson, Bernie Wang, Tim Januschowski, Jan Gasthaus

NeurIPS 2021 · Time series › Causal and generative time series · approach: Robust forecasting and evaluation · 5 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 XLSF instead of conformalized predictionstabular quantile prediction · facebook1P05 loss: 0.471 -> 0.103Improved
use XLSF instead of conformalized predictionstabular quantile prediction · facebook1P95 loss: 0.428 -> 0.288Improved
use XLSF instead of conformalized predictionstabular quantile prediction · facebook1interval accuracy: 94.31% vs 89.98%Hurt
use XLSF instead of QRFtabular quantile prediction · facebook2training time (s): 103.61 -> 14.790Improved
use XLSF instead of QRFtabular quantile prediction · facebook1P95 loss: 0.317 -> 0.288Improved
use XLSF instead of QRFtabular quantile prediction · facebook1P05 loss: 0.094 vs 0.103Hurt
wrap M5 accuracy winner with LSFM5 winning point forecaster · M5 uncertainty bottom levelmean_wQL: 0.35551No clear effect
TTSW (XLSF) instead of DeepARTTSW · electricitymean wQL: 0.0592 -> 0.0499Improved
TTSW (XLSF) instead of DeepARTTSW · trafficmean wQL: 0.0913 -> 0.1212Hurt
TTSW (XLSF) instead of CNN-QRTTSW · partsmean wQL: 0.7566 -> 0.9709Hurt
TTSW (XLSF) instead of CNN-QRTTSW · m4_dailymean wQL: 0.0154 -> 0.0148Improved
TTSW with quantile regression instead of XLSFTTSW · electricitymean wQL: 0.0499 -> 0.1478Hurt

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