AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

AutoMS: Automatic Model Selection for Novelty Detection with Error Rate Control

Yifan Zhang, Haiyan Jiang, Haojie Ren, Changliang Zou, Dejing Dou

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 0 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 AutoMS-JK model selection instead of METAODAutoMS-JK · Shuttle, target FDR 0.1empirical FDR: 0.573 -> 0.100Improved
use AutoMS-JK model selection instead of METAODAutoMS-JK · Shuttle, target FDR 0.1empirical TDR: 0.689 -> 0.942Improved
use AutoMS-JK instead of METAODAutoMS-JK · Covertype, target FDR 0.1empirical TDR: 0.960 -> 0.933Hurt
use AutoMS-JK instead of METAODAutoMS-JK · Credit Card, target FDR 0.1empirical TDR: 0.856 -> 0.758Hurt
select detector with AutoMS-JK instead of best single SRS detectorAutoMS-JK · Credit Card, target FDR 0.1empirical TDR: 0.674 -> 0.758Improved
select detector with AutoMS-JK instead of best single SRS detectorAutoMS-JK · Covertype, target FDR 0.1empirical TDR: 0.890 -> 0.933Improved
select detector with AutoMS-JK instead of best single SRS detectorAutoMS-JK · Satellite, target FDR 0.1empirical TDR: 0.963 -> 0.968No clear effect
use Jackknife prediction instead of split random sampling (SRS) inside AutoMS (ablation)AutoMS · synthetic data, target FDR 0.1TDRImproved
use Jackknife prediction instead of SRS inside AutoMS (ablation)AutoMS · Shuttle, target FDR 0.05empirical TDR: 0.659 -> 0.883Improved
use Jackknife prediction instead of SRS inside AutoMS (ablation)AutoMS · Satellite, target FDR 0.1empirical FDR: 0.134 -> 0.114Improved
raise target FDR level alpha from 0.05 to 0.20AutoMS-JK · Shuttleempirical TDR: 0.883 -> 0.953Improved
choose among detectors and hyperparameters (model selection) rather than fixing one SRS detectorAutoMS · synthetic dataTDRImproved

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