Research map / Learning theory and algorithms / Submodular and game algorithms
Continuous DR-submodular Maximization: Structure and Algorithms
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 |
|---|---|---|---|
| Replace the non-monotone Frank-Wolfe with the two-phase Frank-Wolfe (non-convex Frank-Wolfe subroutine in two down-closed sets, pick the better output) | constrained non-monotone DR-submodular maximization · DR-submodular quadratic, softmax, matched summarization experiments | approximation ratio / function value | Helped |
| Use the shrunken LMO (constraint v <= ubar - x(k)) in the non-monotone Frank-Wolfe variant | non-monotone Frank-Wolfe variant · DR-submodular quadratic synthetic | approximation ratio | No clear effect |
| Use projected gradient ascent with diminishing step sizes instead of the Frank-Wolfe methods | constrained DR-submodular maximization baseline · DR-submodular quadratic, softmax, matched summarization | approximation ratio / function value | Hurt |
Closest papers by meaning
- Gradient Methods for Submodular Maximization (NeurIPS 2017 · similarity 0.92)
- Optimal Continuous DR-Submodular Maximization and Applications to Provable Mean Field Inference (ICML 2019 · similarity 0.91)
- Non-Monotone DR-Submodular Function Maximization (AAAI 2017 · similarity 0.91)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.89)
- From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization (NeurIPS 2024 · similarity 0.89)
- Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints (NeurIPS 2024 · similarity 0.88)
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.