AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Secure Out-of-Distribution Task Generalization with Energy-Based Models

Shengzhuang Chen, Long-Kai Huang, Jonathan Richard Schwarz, Yilun Du, Ying Wei

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 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 prior EBM energy to data-EBM SNLL (energy sum) (ablation)EBML-CNPs · Sinusoids OOD detectionFPR95: 29.40 -> 14.20Improved
Replace EBM prior with Gaussian prior in energy sum (ablation)ABML · Sinusoids OOD detectionFPR95: 61.00 -> 52.20Improved
Add Gaussian prior NLL to SNLL (ablation)CNPs · Sinusoids OOD detectionFPR95: 38.40 -> 34.40Improved
Add Gaussian prior NLL to SNLL (ablation)CNPs · Sinusoids OOD detectionAUROC: 94.81 -> 94.61No clear effect
Use EBML Energy Sum over best OOD baselineEBML · Meta-dataset Simple-CNAPsFPR95: 43.57 -> 6.74Improved
Use EBML Energy Sum over best OOD baselineEBML · Meta-dataset TSAFPR95: 23.83 -> 3.64Improved
Use EBML energy sum instead of Metafun SNLLEBML-CNPs · DrugOODFPR95: 65.17 -> 1.40Improved
Model joint p(X,Y) instead of conditional p(Y|X) (ablation)EBML · DrugOOD OOD detectiondetectionImproved
Use EBM decoder instead of Gaussian decoder (ablation)EBML · multi-sinusoidspredictive distributionImproved
Use EBML-CNPs instead of CNPs for regressionEBML-CNPs · SinusoidsID MSE: 0.009±0.002No clear effect
Use EBML-CNPs instead of CNPsEBML-CNPs · multi-sinusoidsID NLL: 0.58 lowerImproved
Use EBML-CNPs instead of CNPsEBML-CNPs · DrugOODOOD Mean R2: 0.066 -> 0.071Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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