AI Paper Atlas

Research map / Time series / Causal and generative time series

C2FAR: Coarse-to-Fine Autoregressive Networks for Precise Probabilistic Forecasting

Shane Bergsma, Tim Zeyl, Javad Rahimipour Anaraki, Lei Guo

NeurIPS 2022 · Time series › Causal and generative time series · approach: Irregular series and imputation · 7 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
Replace Gaussian output with flat binning (C2FAR-1) (ablation)DeepAR · AzureND%: 3.60 -> 2.95Improved
Replace Gaussian output with flat binning (C2FAR-1) (ablation)DeepAR · WikiwQL%: 54.7 -> 21.3Improved
Replace Gaussian output with flat binning (C2FAR-1) (ablation)DeepAR · TrafficND%: 16.1 -> 13.0Improved
Go from one level to two levels (C2FAR-1 to C2FAR-2) (ablation)C2FAR · AzureND%: 2.95 -> 2.86Improved
Go from two levels to three levels (C2FAR-2 to C2FAR-3) (ablation)C2FAR · AzureND%: 2.86 -> 2.77Improved
Go from one level to three levels (ablation)C2FAR · ElectricityND%: 6.14 -> 6.00Improved
Go from one level to two or three levels (ablation)C2FAR · TrafficND%: 12.9 -> 13.3Hurt
Go from one level to two levels (ablation)C2FAR · WikiwQL%: 21.3 -> 21.0Improved
Use C2FAR-2 instead of DeepAR-Gaussian for calibrationC2FAR · AzureCov80: 89.9/16.9 -> 79.0/8.5Improved
Use C2FAR-3 vs DeepAR-Gaussian on extreme percentileC2FAR · AzureCov99: 98.0/37.7 -> 98.6/32.7Improved
Deeper C2FAR on synthetic discrete data (level 1 to 3) (ablation)C2FAR · Synthetic discrete uniformtest NLL: -1.564 -> -6.664Improved
Deeper C2FAR on Gaussian mixture (level 1 to 3) (ablation)C2FAR · Synthetic Gaussian mixturetest NLL: -0.4150 -> -0.4203Improved

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