AI Paper Atlas

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

Geometry- and Accuracy-Preserving Random Forest Proximities

Jake S. Rhodes, Adele Cutler, Kevin R. Moon

TPAMI 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Approximate nearest neighbor indexing · 217 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
replace original proximity with RF-GAPproximity-weighted prediction · 24 UCI datasetstrain/test error slope: 2.434 -> 1.040Improved
replace OOB proximity with RF-GAPproximity-weighted prediction · 24 UCI datasetstrain/test error slope: 1.543 -> 1.040Improved
replace PBK with RF-GAPproximity-weighted prediction · 24 UCI datasetstrain/test error slope: 2.287 -> 1.040Improved
replace RFProxIH with RF-GAPproximity-weighted prediction · 24 UCI datasetstrain/test error slope: 2.147 -> 1.040Improved
replace original proximity with RF-GAPrandom forest imputation · UCI, 5% MCARaverage rank: 2.55 -> 1.10Improved
replace original proximity with RF-GAPrandom forest imputation · UCI, 75% MCARaverage rank: 2.35 -> 1.65Improved
replace OOB proximity with RF-GAPrandom forest imputation · UCI, 50% MCARaverage rank: 2.40 -> 1.35Improved
replace RFProxIH with RF-GAPrandom forest imputation · UCI, 25% MCARaverage rank: 3.33 -> 1.15Improved
increase missing rate from 5% to 75%RF-GAP imputation · UCI MCARaverage rank: 1.10 -> 1.65Hurt
replace original proximity with RF-GAPproximity-weighted prediction vs RF · Diabetesmismatch with RF predictions: 0.052 -> 0.001Improved
prune trees (minimum node size up to 50)RF-GAP classification · classification datasetsmatch with RF predictionsNo clear effect
replace original proximity with RF-GAP for MDS visualizationMDS on proximities · Sonarvisual class separationImproved

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