AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

GAR: Generalized Autoregression for Multi-Fidelity Fusion

Yuxin Wang, Zheng Xing, WEI W. XING

NeurIPS 2022 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine learning for physical simulation · 1 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
Add flexible linear transformation (GAR) to the autoregressive AR modelAR · Canonical PDEsRMSE: up to 6x reduction in RMSEImproved
Use CIGAR instead of GAR (no hard orthogonality constraint on weights)GAR · Canonical PDEsRMSEHurt
Unaligned instead of aligned outputsMF-BNN · Canonical PDEsRMSEHurt
Unaligned instead of aligned outputsGAR/CIGAR · Canonical PDEsRMSENo clear effect
Remove ECD from low-fidelity training data (ablation)GAR/CIGAR · SOFCRMSEHurt
Increase number of high-fidelity training samplesCIGAR · Topology optimizationRMSEImproved
Use GAR/CIGAR instead of MF-BNNGAR/CIGAR · Topology optimization and SOFCconvergence rate in epochs: more than 10x fasterImproved

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