AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Compact Autoregressive Network

Di Wang, Feiqing Huang, Jingyu Zhao, Guodong Li, Guangjian Tian

AAAI 2020 · Architectures and efficiency › RNNs and normalization · approach: LSTM design and memory · 2 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 Tucker-factorized TAR-2 instead of RNNUS macroeconomic forecasting · US macroeconomic dataset, rolling forecastRMSE: 0.9217 -> 0.8958Improved
Add a second parallel lane to TAR (ablation)TAR · US macroeconomic dataset, rolling forecastRMSE: 0.9104 -> 0.8958Improved
Add nonlinear activations to LTAR (ablation)LTAR · NL-DGP, T=500RMSE: 1.0126 -> 1.0110Improved
Add nonlinear activations to LTAR (ablation)LTAR · L-DGP, T=100RMSE: 1.0388 -> 1.0998Hurt
Use two parallel lanes instead of one (ablation)TAR · L-DGP, T=100RMSE: 1.0998 -> 1.1238Hurt
Use two parallel lanes instead of one (ablation)TAR · L-DGP, T=500RMSE: 1.0585 -> 1.0493Improved
Use two parallel lanes instead of one (ablation)TAR · NL-DGPRMSE: 1.0712 -> 1.0703; 1.0110 -> 1.0111Mixed
Use Tucker structure over ordinary least squaresLinear autoregressive network · Linear autoregressive estimationsample complexity: N^2P/ε^2; (r_1r_2r_3+Nr_1+Nr_2+Pr_3)/ε^2Improved

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