AI Paper Atlas

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

CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints

Anselm Paulus, Michal Rolinek, Vit Musil, Brandon Amos, Georg Martius

ICML 2021 · Learning theory and algorithms › Combinatorial and search optimization · approach: Semidefinite relaxations for verification · 12 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 CombOptNet instead of BB-GM with unary costs onlykeypoint matching · Keypoint matching, 4×4 through 7×7per-variable accuracy (%): 84.3 -> 83.1; 81.6 -> 80.7; 79.0 -> 78.6; 76.5 -> 76.1Hurt
Use CombOptNet instead of BB-GM with unary and quadratic costskeypoint matching · Keypoint matching, 4×4 through 7×7per-variable accuracy (%): 84.3 -> 83.1; 82.9 -> 80.7; 80.5 -> 78.6; 79.8 -> 76.1Hurt
Replace the Δ basis with the canonical basis (ablation)CombOptNet · Random Constraints, binary, 4 ground-truth constraintsevaluation accuracy (%): 77.4 + 13.5 -> 14.4 + 3.2Hurt
Replace the Δ basis with the canonical basis (ablation)CombOptNet · Random Constraints, dense, 4 ground-truth constraintsevaluation accuracy (%): 29.6 + 10.4 -> 26.8 + 4.1No clear effect
Replace the Δ basis with the canonical basis (ablation)CombOptNet · Weighted Set Covering, 8 ground-truth constraintsevaluation accuracy (%): 79.7 + 12.1 -> 0.2 + 0.3Hurt
Replace the softened minimum with a hard minimum (ablation)CombOptNet · Random Constraints, binary, 4 ground-truth constraintsevaluation accuracy (%): 77.4 + 13.5 -> 55.4 + 18.9Hurt
Replace the softened minimum with a hard minimum (ablation)CombOptNet · Random Constraints, dense, 4 ground-truth constraintsevaluation accuracy (%): 29.6 + 10.4 -> 21.4 + 10.7Hurt
Replace the softened minimum with a hard minimum (ablation)CombOptNet · Weighted Set Covering, 8 ground-truth constraintsevaluation accuracy (%): 79.7 + 12.1 -> 45.1 + 14.1Hurt
Increase the soft-minimum temperature from τ=0.5 to τ=1.0 (ablation)CombOptNet · Weighted Set Covering, 8 ground-truth constraintsevaluation accuracy (%): 79.7 + 12.1 -> 70.3 + 15.5Hurt
Replace the MSE loss with L0 loss (ablation)CombOptNet · Random Constraints, dense, 4 ground-truth constraintsevaluation accuracy (%): 29.6 + 10.4 -> 15.3 + 4.3Hurt
Increase the number of learnable constraints from 1×m to 4×m (ablation)CombOptNet · Random Constraints, binary, 8 ground-truth constraintsevaluation accuracy (%): 46.5 + 12.4 -> 77.7 + 3.2Improved
Increase the number of learnable constraints from 1 to 2 (ablation)CombOptNet · Weighted Set Covering, 8 ground-truth constraintsevaluation accuracy (%): 79.7 + 12.1 -> 99.3 + 0.8Improved

Later papers that compared with this method

2 later accepted papers report CombOptNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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