Research map / Learning theory and algorithms / Submodular and game algorithms
Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization
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 |
|---|---|---|---|
| Local search (LOCAL-SEARCH) with greedy-initialized potential instead of baselines | two-stage submodular maximization on Wikipedia coverage objective · Wikipedia (ML category, n=575, m=23) | objective value (vertex cover / coverage) | Helped |
| Local search compared with GREEDY-SUM, MODULAR-APPROX baselines | image collection summarization · Images (100 images, 8 categories) | objective value | Helped |
| Continuous optimization (CONTINUOUS-OPT) versus baselines | two-stage submodular maximization · Wikipedia and Images | objective value | Hurt |
| Modular approximation of second-stage submodular functions (MODULAR-APPROX) vs greedy-sum | two-stage submodular maximization · Images and Wikipedia | objective value | Hurt |
Closest papers by meaning
- Data Summarization at Scale: A Two-Stage Submodular Approach (ICML 2018 · similarity 0.89)
- Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach (NeurIPS 2017 · similarity 0.88)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.88)
- Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy? (ICML 2018 · similarity 0.88)
- Dynamic Submodular Maximization (NeurIPS 2020 · similarity 0.88)
- Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint (NeurIPS 2024 · 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.