Research map / Learning theory and algorithms / Submodular and game algorithms
Optimal Sequential Maximization: One Interview is Enough!
Moein Falahatgar, Alon Orlitsky, Venkatadheeraj Pichapati
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 multi-round elimination with a sequential anchor-based algorithm (OPT-AGNOSTIC-SEQ) that adaptively updates anchor with asymmetric checkpoints | dueling bandits probabilistic maximization with SST · simulated pairwise model, 0.05-maximum, delta=0.1 | comparison complexity | Improved |
| make SEQ-ELIMINATE n-agnostic by using confidence delta/(2i^2) per comparison (ablation) | SEQ-ELIMINATE · simulated pairwise model, 0.05-maximum, delta=0.1 | comparison complexity | Hurt |
| use asymmetric confidence checkpoints (A-T) for anchor updates in traditional bandits | O-S sequential maximization · theoretical query complexity | query complexity | Improved |
Closest papers by meaning
- Optimal Design for Human Preference Elicitation (NeurIPS 2024 · similarity 0.84)
- On Bits and Bandits: Quantifying the Regret-Information Trade-off (ICLR 2025 · similarity 0.83)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 2024 · similarity 0.83)
- Ranking with Multiple Oracles: From Weak to Strong Stochastic Transitivity (ICML 2025 · similarity 0.83)
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming (NeurIPS 2025 · similarity 0.83)
- Streaming Stochastic Submodular Maximization with On-Demand User Requests (NeurIPS 2025 · similarity 0.83)
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.
