Research map / Optimization / Nonconvex and smooth optimization
Accelerated Message Passing for Entropy-Regularized MAP Inference
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 |
|---|---|---|---|
| Apply Nesterov-inspired randomized acceleration to EMP | EMP · MAP inference over L2 | iterations sufficient for expected epsilon-optimality: O(1/ε^3) -> O(1/ε^2) | Helped |
| Apply Nesterov-inspired randomized acceleration to SMP | SMP · MAP inference over L2 | iterations sufficient for expected epsilon-optimality: O(1/ε^3) -> O(1/ε^2) | Helped |
| Use accelerated rather than standard message passing | EMP and SMP · Synthetic Erdős-Rényi graph, primal objective | primal objective error | No clear effect |
| Use accelerated rather than standard message passing | EMP and SMP · Synthetic Erdős-Rényi graphs | log-competitive ratio | Helped |
| Use SMP instead of EMP | Standard message passing · Synthetic Erdős-Rényi graph | convergence iterations | Helped |
| Use EMP instead of coordinate descent | Standard coordinate descent · Synthetic Erdős-Rényi graph | convergence iterations | Helped |
Closest papers by meaning
- Newton-Type Methods for Inference in Higher-Order Markov Random Fields (CVPR 2017 · similarity 0.90)
- Convergence of Some Convex Message Passing Algorithms to a Fixed Point (ICML 2024 · similarity 0.89)
- Continuous Relaxation of MAP Inference: A Nonconvex Perspective (CVPR 2018 · similarity 0.88)
- The Theory and Practice of MAP Inference over Non-Convex Constraints (ICML 2026 · similarity 0.87)
- One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes (ICML 2022 · similarity 0.86)
- MAP Estimation with Denoisers: Convergence Rates and Guarantees (NeurIPS 2025 · similarity 0.84)
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.