AI Paper Atlas

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

DivBO: Diversity-aware CASH for Ensemble Learning

Yu Shen, Yupeng Lu, Yang Li, Yaofeng Tu, Wentao Zhang, Bin CUI

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 4 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
add diversity-aware surrogate to BO-ES (DivBO)BO-ES · 15 datasetsaverage rank (test error): 3.13 -> 1.73Improved
DivBO vs strongest baseline RB-ESpost-hoc ensemble · 15 datasetsaverage rank (test error): 2.90 -> 1.73Improved
DivBO vs RB-ES statistical testpost-hoc ensemble · 15 datasetsdatasets better/same/worse: 8 better, 4 same, 3 worseMixed
DivBO vs RS-ES statistical testpost-hoc ensemble · 15 datasetsdatasets better/same/worse: 13 better, 2 same, 0 worseImproved
DivBO vs BO-ES statistical testpost-hoc ensemble · 15 datasetsdatasets better/same/worse: 12 better, 1 same, 2 worseImproved
fix diversity weight at 0.1 instead of scheduling (ablation)DivBO · poltest error (%): 1.34 -> 1.66Hurt
fix diversity weight at 0.1 instead of scheduling (ablation)DivBO · quaketest error (%): 45.55 -> 45.63No clear effect
fix diversity weight at 0.1 instead of scheduling (ablation)DivBO · house_8Ltest error (%): 10.80 -> 11.51Hurt
use bagging instead of ensemble selection (ablation)DivBO · elevatorstest error (%): 9.40 -> 10.98Hurt
use stacking instead of ensemble selection (ablation)DivBO · poltest error (%): 1.34 -> 1.54Hurt
increase ensemble size from 25 to 100 (ablation)BO-ES · quaketest error (%): 46.10 -> 47.43Hurt
increase ensemble size from 25 to 100 (ablation)BO-ES · windtest error (%): 14.04 -> 14.04No clear effect

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