atlas

Research map / Learning theory and algorithms / Sample complexity

Trimmed Density Ratio Estimation

NeurIPS 2017 · Learning theory and algorithms › Sample complexity · approach: Density and property estimation · 7 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
Trim high log-density-ratio samples using TR-DRE with ν = 90%Density ratio estimation for sparse Markov-network changes with an injected outlier · Gaussian Markov networkstrue positive rateHelped
Add one outlier to the data used by standard DREDRE for sparse Markov-network changes · Gaussian Markov networkstrue positive rateHurt
Trim samples with high density ratios (ablation)TR-DRE for sparse Markov-network changes · Gaussian Markov networkstrue positive rateHurt
Increase the number of high-ratio windows selected by tuning ν (ablation)TR-DRE for relative novelty detection · Relative novelty detection from imagesrelative novelty detectionMixed
Use the reference dataset Q when scoring image windowsTR-DRE · Relative novelty detection from imagesrelative novelty detectionHelped
Select the top 3% highest density-ratio windows using thresholded DREThresholded-DRE · Relative novelty detection from imagesrelative novelty detectionMixed

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