AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression

Steve Yadlowsky, Taedong Yun, Cory Y McLean, Alexander D'Amour

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 3 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
Apply SLOE dimensionality correction instead of standard inferenceLogistic regression MLE · Simulations with Gaussian and simulated GWAS features90% CI coverage: 90%Improved
Use standard inference instead of SLOE dimensionality correctionLogistic regression MLE · Simulations, κ > 0.0590% CI coverage: κ > 0.05Hurt
Use SLOE rather than ProbeFrontier to estimate signal strengthLogistic regression inference · Simulations, κ = 0.2, γ² = 1runtime speedup: 10x fasterImproved
Use SLOE rather than ProbeFrontier to estimate signal strengthLogistic regression inference · Simulations, n ≳ 3000runtime speedup: 100x fasterImproved
Use SLOE-corrected rather than standard p-valuesGlaucoma logistic regression · UK Biobank glaucoma variantsnull p-value calibrationImproved
Use SLOE-corrected rather than standard p-valuesGlaucoma logistic regression · UK Biobank glaucoma variantsfalse discovery proportion calibrationImproved
Use standard rather than SLOE-corrected confidence intervalsHeart disease logistic regression predictions · Cleveland Clinic Heart Diseaseprediction confidence calibration: 1.40Hurt
Use nonparametric bootstrap confidence intervals instead of dimensionality-corrected intervalsLogistic regression predictions · Heart Disease application settingCI coverageHurt

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