AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Normalizing Flows for Knockoff-free Controlled Feature Selection

Derek Hansen, Brian Manzo, Jeffrey Regier

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Flow-based density estimation · 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
use FlowSelect instead of DDLKcontrolled feature selection · scRNA-seq runtimemedian runtime (min): 91.9 -> 59.4Improved
use FlowSelect instead of DeepKnockoffcontrolled feature selection · scRNA-seq runtimemedian runtime (min): 3.0 -> 59.4Hurt
use FlowSelect instead of KnockoffGANcontrolled feature selection · scRNA-seq runtimemedian runtime (min): 3.73 -> 59.4Hurt
use FlowSelect instead of MASScontrolled feature selection · scRNA-seq runtimemedian runtime (min): 12.6 -> 59.4Hurt
replace deep knockoff generators (DeepKnockoff, KnockoffGAN, MASS, DDLK) with FlowSelect conditional randomization testFlowSelect · Mixture-of-Gaussians and scRNA-seq, targets 0.05/0.1/0.25FDR controlImproved
replace knockoff methods that do control FDR with FlowSelectFlowSelect · Mixture-of-Gaussians and scRNA-seqpowerImproved
give MASS the true data distributionMASS · Mixture-of-GaussiansFDR controlNo clear effect
use oracle Model-X knockoffs with true parameters versus FlowSelectOracle Model-X · Mixture-of-GaussianspowerHurt
give DDLK the exact joint densityDDLK · Mixture-of-GaussiansFDR and powerNo clear effect
replace normalizing flow with mixture density networks (HRT) (ablation)FlowSelect · Mixture-of-GaussiansFDR controlHurt
replace normalizing flow with mixture density networks (HRT) (ablation)FlowSelect · scRNA-seqpower and FDRNo clear effect
increase number of MCMC samples (ablation)FlowSelect · scRNA-seqpowerImproved

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