AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

NOMU: Neural Optimization-based Model Uncertainty

Jakob M Heiss, Jakob Weissteiner, Hanna S Wutte, Sven Seuken, Josef Teichmann

ICML 2022 · Probabilistic and scientific modeling › Bayesian optimization · approach: Multi-fidelity hyperparameter optimization · 5 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 NOMU's two-subnetwork architecture and designed uncertainty loss instead of the compared uncertainty estimatorsNeural-network model uncertainty estimation · BNN-generated regression test bedNLPD: BNN1D: -1.65± 0.10 vs -1.08± 0.22; BNN2D: -1.16± 0.05 vs -0.77± 0.07; BNN5D: -0.37± 0.02 vs -0.33± 0.02Improved
Use NOMU uncertainty bounds as the BO acquisition functionBayesian optimization · BO average regret 5Dfinal regret: 2.87e-02 vs 4.14e-02Improved
Use NOMU uncertainty bounds as the BO acquisition functionBayesian optimization · BO average regret 10Dfinal regret: 8.40e-02 vs 6.96e-02Mixed
Use NOMU uncertainty bounds as the BO acquisition functionBayesian optimization · BO average regret 20Dfinal regret: 1.12e-01 vs 1.17e-01Improved
Use NOMU rather than MCDO for uncertainty estimationNeural-network regression · UCI BostonNLPD: 2.68 ± 0.11 vs 2.40 ± 0.07Hurt
Use NOMU rather than NLM-HPO for uncertainty estimationNeural-network regression · UCI EnergyNLPD: 0.77 ± 0.06 vs 0.69 ± 0.05Hurt
Use MC dropout for model uncertainty estimationNeural-network regression · Noiseless scarce-data toy regressionin-sample uncertainty behaviorHurt
Use HDE for model uncertainty estimationNeural-network regression · Noiseless scarce-data toy regressionout-of-sample uncertainty behaviorHurt

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