AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Autofocused oracles for model-based design

Clara Fannjiang, Jennifer Listgarten

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 16 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 iterative importance-weighted oracle retraining to CbASCbAS · Superconductorsmedian ground-truth expectation (K): 51.5 -> 76.4Improved
Add iterative importance-weighted oracle retraining to DbASDbAS · Superconductorsmedian ground-truth expectation (K): 57.0 -> 78.9Improved
Add iterative importance-weighted oracle retraining to RWRRWR · Superconductorsmedian ground-truth expectation (K): 43.4 -> 71.4Improved
Add iterative importance-weighted oracle retraining to FBFB · Superconductorsmedian ground-truth expectation (K): 49.2 -> 64.2Improved
Add iterative importance-weighted oracle retraining to CEM-PICEM-PI · Superconductorsmedian ground-truth expectation (K): 34.5 -> 67.0Improved
Add iterative importance-weighted oracle retraining to CMA-ESCMA-ES · Superconductorsmedian ground-truth expectation (K): 42.1 -> 50.2Improved
Add iterative importance-weighted oracle retraining to RWRRWR · SuperconductorsSpearman correlation: 0.92 -> 0.65Hurt
Add iterative importance-weighted oracle retraining to RWRRWR · SuperconductorsRMSE (K): 7.4 -> 12.7Hurt
Add iterative importance-weighted oracle retraining to DbASDbAS · SuperconductorsSpearman correlation: 0.01 -> 0.01No clear effect
Use unflattened importance weights (alpha = 1) instead of flattening weights to alpha = 0.2 during autofocusing (ablation)Superconductors experiments across MBO methods · Superconductorsdesign metrics and oracle-ground-truth agreementMixed
Use autofocusing without importance-weight variance control (ablation)CMA-ES · Superconductorsdesign metricsMixed
Apply autofocusing in the illustrative example across training-distribution and label-noise settingsCbAS · One-dimensional multimodal design problemground-truth design objectiveImproved

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