AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Bidirectional Learning for Offline Infinite-width Model-based Optimization

Can Chen, Yingxue Zhang, Jie Fu, Xue Liu, Mark Coates

NeurIPS 2022 · Probabilistic and scientific modeling › Bayesian optimization · approach: Offline black-box optimization with surrogates · 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
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · Superconductor100th percentile normalized ground truth score: 0.488 ± 0.034 -> 0.520 ± 0.005Improved
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · Ant Morphology100th percentile normalized ground truth score: 1.214 ± 0.732 -> 0.962 ± 0.000Hurt
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · D’Kitty Morphology100th percentile normalized ground truth score: 0.942 ± 0.010 -> 0.941 ± 0.000No clear effect
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · Hopper Controller100th percentile normalized ground truth score: 1.959 ± 0.159 -> 1.989 ± 0.050Improved
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · GFP100th percentile normalized ground truth score: 0.865 ± 0.000 -> 0.864 ± 0.000No clear effect
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · TF Bind 8100th percentile normalized ground truth score: 0.953 ± 0.022 -> 0.973 ± 0.000Improved
Use bidirectional learning with the NTK model rather than the strongest reported baselineOffline model-based optimization · UTR100th percentile normalized ground truth score: 0.699 ± 0.011 -> 0.760 ± 0.000Improved
Add the forward mapping loss (ablation)BDI · TF Bind 8100th percentile normalized ground truth score: 0.984 ± 0.000 -> 0.973 ± 0.000Hurt
Add the forward mapping loss (ablation)BDI · GFP, UTR, Superconductor, Ant Morphology, D’Kitty Morphology, Hopper Controller100th percentile normalized ground truth score: GFP: 0.860 ± 0.004 -> 0.864 ± 0.000; UTR: 0.636 ± 0.000 -> 0.760 ± 0.000; SuperC: 0.511 ± 0.007 -> 0.520 ± 0.005; Ant: 0Improved
Add the backward mapping loss (ablation)BDI · UTR100th percentile normalized ground truth score: 0.777 ± 0.000 -> 0.760 ± 0.000Hurt
Add the backward mapping loss (ablation)BDI · Superconductor, Ant Morphology, Hopper Controller100th percentile normalized ground truth score: SuperC: 0.502 ± 0.007 -> 0.520 ± 0.005; Ant: 0.933 ± 0.000 -> 0.962 ± 0.000; Hopper: 1.821 ± 0.223 -> 1.989 ± 0.050Improved
Add the backward mapping loss (ablation)BDI · GFP, TF Bind 8, D’Kitty Morphology100th percentile normalized ground truth score: GFP: 0.864 ± 0.000 -> 0.864 ± 0.000; TFB: 0.973 ± 0.000 -> 0.973 ± 0.000; D’Kitty: 0.942 ± 0.001 -> 0.941 ± 0.000No clear effect

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