Research map / Learning theory and algorithms / Combinatorial and search optimization
Train and Test Tightness of LP Relaxations in Structured Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Train with LP relaxation instead of exact inference | Structured prediction · Dependency parsing test data | integral solutions (%): 83.47% -> 92.88% | Helped |
| Train with LP relaxation instead of exact inference | Structured prediction · Yeast | integral instances (%): 17.7% -> 99.57% | Helped |
| Use random labels instead of ground-truth labels during LP-relaxed training (ablation) | Multi-label classification · Multi-label classification with random labels | tight training instances (%): 100% | No clear effect |
| Train with exact inference instead of LP-relaxed inference | Structured prediction · Noisy Scene | tight instances | Hurt |
| Use noisy singleton features, increasing reliance on pairwise interactions (ablation) | Scene model · Noisy Scene | tight instances | Hurt |
Closest papers by meaning
- LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured Prediction (ICML 2020 · similarity 0.87)
- Learning SMaLL Predictors (NeurIPS 2018 · similarity 0.86)
- Exact MAP-Inference by Confining Combinatorial Search With LP Relaxation (AAAI 2018 · similarity 0.86)
- Differentiable Dynamic Programming for Structured Prediction and Attention (ICML 2018 · similarity 0.86)
- Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning (NeurIPS 2026 · similarity 0.85)
- Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses (NeurIPS 2026 · similarity 0.85)
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.