AI Paper Atlas

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

Online Agnostic Multiclass Boosting

Vinod Raman, Ambuj Tewari

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 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 online agnostic boosting (Agn) instead of OnlineMBBMOnlineMBBM · UCI Balanceaccuracy: 79.5 -> 84.4Improved
use Agn instead of OnlineMBBMOnlineMBBM · UCI Carsaccuracy: 69.9 -> 80.6Improved
use Agn instead of OnlineMBBMOnlineMBBM · UCI Miceaccuracy: 77.6 -> 86.0Improved
use Agn instead of OnlineMBBMOnlineMBBM · UCI Landsataccuracy: 80.8 -> 67.0Hurt
use Agn instead of OnlineMBBMOnlineMBBM · UCI Abaloneaccuracy: 24.9 -> 22.1Hurt
use Agn instead of OnlineMBBMOnlineMBBM · UCI Abaloneruntime (s): 9775.3 -> 4036.7Improved
use OCO-based realizable boosting (OCOR) instead of OnlineMBBMOnlineMBBM · UCI Segmentaccuracy: 78.9 -> 79.3No clear effect
use OCOR instead of OnlineMBBMOnlineMBBM · UCI Landsatruntime (s): 1814.3 -> 440.4Improved
use OCOR instead of OnlineMBBMOnlineMBBM · UCI Yeastaccuracy: 39.8 -> 47.6Improved
use Adaboost.OLM instead of OnlineMBBMOnlineMBBM · UCI Landsatruntime (s): 1814.3 -> 81.8Improved
use Adaboost.OLM instead of OnlineMBBMOnlineMBBM · UCI Landsataccuracy: 80.8 -> 56.9Hurt
use random relabeling instead of fractional relabeling (ablation)Agn · UCI datasetsaccuracy and speedMixed

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