Research map / Learning theory and algorithms / Combinatorial and search optimization
Graph Cuts Always Find a Global Optimum for Potts Models (With a Catch)
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 |
|---|---|---|---|
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · tsukuba | Hamming error upper bound: 0.821 -> 0.290 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · venus | Hamming error upper bound: 0.703 -> 0.375 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · plastic | Hamming error upper bound: 0.779 -> 0.373 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · road | Hamming error upper bound: 0.256 -> 0.171 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · bikes | Hamming error upper bound: 0.229 -> 0.146 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · car | Hamming error upper bound: 0.225 -> 0.081 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · tsukuba | objective gap upper bound: 1.228 -> 1.213 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · venus | objective gap upper bound: 1.268 -> 1.199 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · plastic | objective gap upper bound: 1.095 -> 1.073 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · road | objective gap upper bound: 1.036 -> 1.031 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · bikes | objective gap upper bound: 1.030 -> 1.027 | Helped |
| Use the proposed perturbation-based bound instead of the naive approximation-guarantee bound | MAP inference Potts instances · car | objective gap upper bound: 1.047 -> 1.019 | Helped |
Closest papers by meaning
- Asynchronous Parallel Coordinate Minimization for MAP Inference (NeurIPS 2017 · similarity 0.87)
- Solving Constrained Combinatorial Optimisation Problems via MAP Inference without High-Order Penalties (AAAI 2017 · similarity 0.87)
- From Fields to Random Trees (ICLR 2026 · similarity 0.87)
- Anytime Best+Depth-First Search for Bounding Marginal MAP (AAAI 2017 · similarity 0.87)
- Exact MAP-Inference by Confining Combinatorial Search With LP Relaxation (AAAI 2018 · similarity 0.87)
- Exact MAP Inference by Avoiding Fractional Vertices (ICML 2017 · similarity 0.87)
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.