AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Deep Direct Likelihood Knockoffs

NeurIPS 2020 · Probabilistic and scientific modeling › Molecules and proteins · approach: Statistical analysis of ML practice · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 DDLK instead of the baseline knockoff generatorsKnockoff feature selection · COVID-19 adverse eventsselected features: 10 vs 5, 4, and 4Helped
Use DDLK instead of the baseline generatorsKnockoff feature selection · COVID-19 adverse eventsdoctor-validated selected features: 8 of which were found to be meaningfulHelped
Use DDLK rather than baseline generatorsKnockoff feature selection · mixture synthetic benchmarkpowerHelped
Use DDLK rather than the baselinesKnockoff feature selection · gene semi-synthetic benchmarkpowerMixed
Set entropy regularization to λ ≤ 0.1 (ablation)DDLK · Gaussian synthetic benchmark across tested correlationsFDP calibration: λ ≤ 0.1Helped
Increase entropy regularization λ (ablation)DDLK · Gaussian synthetic benchmarkFDPHurt
Increase entropy regularization λ (ablation)DDLK · Gaussian synthetic benchmark with weaker covariate correlationsFDP increaseMixed

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