AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

How hard is learning to cut? Trade-offs and sample complexity

Sammy Khalife, Andrea Lodi

ICLR 2026 · Learning theory and algorithms › Sample complexity · approach: Sample complexity of ranking and selection · 1 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
train GNN on gap closed instead of B&C tree size (ablation)GNN cut selector · Set coveraverage tree size: 8.27 -> 8.65Hurt
train GNN on gap closed instead of B&C tree size (ablation)GNN cut selector · Facility locationaverage tree size: 128.85 -> 134.61Hurt
use GNN (tree size) instead of Parallelism heuristicGNN cut selector · Set coveraverage tree size: 8.29 -> 8.27No clear effect
use GNN (tree size) instead of Parallelism heuristicGNN cut selector · Facility locationaverage tree size: 144.09 -> 128.85Improved
use GNN (gap closed) instead of random selectionGNN cut selector · Facility locationaverage tree size: 152.46 -> 134.61Improved

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