AI Paper Atlas

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

MERCS: Multi-Directional Ensembles of Regression and Classification Trees

Elia Van Wolputte, Evgeniya Korneva, Hendrik Blockeel

AAAI 2018 · Learning theory and algorithms › Prediction and decision losses · approach: Tree ensemble optimization · 11 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 multi-target trees (p in 2..10) instead of single-target trees (p=1) (ablation)MERCS · 11 density-estimation datasets (e.g. voting, msnbc)model induction timeImproved
use multi-target trees instead of single-target trees (ablation)MERCS · 11 datasetsmacro F1 per queryNo clear effect
MA-prediction instead of MI-prediction with random selection strategy (ablation)MERCS · datasets with random tree selectionmacro F1 per queryImproved
MA-prediction instead of MI-prediction with default selection strategy (ablation)MERCS · datasets with default selectionmacro F1 per queryNo clear effect
MERCS instead of PGM (BayesFusion)MERCS vs BayesFusion · nominal datasetsinference time per query: up to about 3 orders of magnitude fasterImproved
MERCS instead of PGM (BayesFusion)MERCS vs BayesFusion · datasets with many attributes (voting)induction timeMixed
MERCS instead of PGM (BayesFusion)MERCS vs BayesFusion · 12 datasetsmacro F1 per query: loses in 7 cases, wins in 5Mixed

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