AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Learning Hard Optimization Problems: A Data Generation Perspective

James Kotary, Ferdinando Fioretto, Pascal Van Hentenryck

NeurIPS 2021 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization · 21 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
Generate JSS targets sequentially, choosing optimal solutions close to the adjacent instanceJSS learning with Optimal Design data · JSS ta25prediction error: 193.9 -> 23.4Improved
Generate JSS targets sequentially, choosing optimal solutions close to the adjacent instanceJSS learning with Optimal Design data · JSS swv03optimality gap (%): 18.0 -> 2.2Improved
Generate JSS targets sequentially, choosing optimal solutions close to the adjacent instanceJSS learning with Optimal Design data · JSS swv11prediction error: 1090.0 -> 51.2Improved
Generate OPF targets using consistent generator commitments that remove symmetriesOPF learning with Optimal Design data · Pegase-89prediction error: 89.17 -> 2.78Improved
Generate OPF targets using consistent generator commitments that remove symmetriesOPF learning with Optimal Design data · Pegase-89constraint violation: 1.353 -> 0.003Improved
Generate OPF targets using consistent generator commitments that remove symmetriesOPF learning with Optimal Design data · IEEE-118optimality gap (%): 3.80 -> 0.36Improved

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