atlas

Research map / Time series / Long-term forecasting

Probabilistic Transformer For Time Series Analysis

NeurIPS 2021 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models · 32 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
add second stochastic layer (ablation)one-layer ProTran · TRAFFICCRPSsum (lower better): 0.031 -> 0.028Helped
add context attention (ablation)one-layer ProTran · TRAFFICCRPSsum (lower better): 0.033 -> 0.031Helped
add stochastic latent variables to w_t (vs deterministic) (ablation)one-layer ProTran · TRAFFICCRPSsum (lower better): 0.041 -> 0.031Helped
use ProTran instead of TimeGradforecasting · TRAFFICCRPSsum (lower better): 0.044 -> 0.028Helped
use ProTran instead of TimeGradforecasting · ELECTRICITY, WIKIPEDIACRPSsum (lower better): 0.021 -> 0.016 (ELECTRICITY); 0.049 -> 0.047 (WIKIPEDIA)No clear effect
use ProTran instead of DLowhuman motion prediction · Human3.6M, HumanEva-IADE/FDE (lower better): ADE 0.425 -> 0.381, FDE 0.518 -> 0.491 (Human3.6M); ADE 0.251 -> 0.258, FDE 0.268 -> 0.255 (HumanEva-I)Mixed

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