Research map / Bandits and online learning / Online convex optimization and games
Bandit Multi-linear DR-Submodular Maximization and Its Applications on Adversarial Submodular Bandits
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 standard one-point gradient estimator with multi-linear-specific estimator exploiting that gradients are linear combinations of finite function values | BanditMLSM · bandit multi-linear DR-submodular maximization | (1-1/e)-regret | Helped |
| use smoothness of online functions with self-concordant RFTL and non-oblivious technique for general DR-submodular bandits | BanditDRSM · general bandit monotone DR-submodular maximization | (1-1/e)-regret exponent in T: T^{3/4} vs prior T^{5/6} | Helped |
| continuous extension reduction for partition matroid instead of multi-linear extension of set function | submodular bandit with partition matroid constraint · bandit monotone submodular maximization over partition matroid | (1-1/e)-regret exponent in T | Helped |
| continuous extension reduction for bandit sequential submodular maximization | bandit sequential submodular maximization · bandit sequential submodular maximization | approximation ratio: from 1/2 to 1-1/e | Helped |
Closest papers by meaning
- Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints (NeurIPS 2024 · similarity 0.91)
- Online Submodular Maximization via Online Convex Optimization (AAAI 2024 · similarity 0.90)
- Nearly Minimax Optimal Submodular Maximization with Bandit Feedback (NeurIPS 2024 · similarity 0.90)
- From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization (NeurIPS 2024 · similarity 0.90)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.90)
- Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization (ICLR 2024 · similarity 0.89)
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.