Research map / Learning theory and algorithms / Submodular and game algorithms
Buying Information for Stochastic Optimization
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 |
|---|---|---|---|
| Use the path-based Q estimator and stop when it reaches 1 | Super-martingale stopping · Super-martingale stopping | competitive ratio: 2 | Helped |
| Randomize the stopping threshold using density p(ρ)=e^ρ/(e-1) | Super-martingale stopping · Super-martingale stopping | competitive ratio: e/(e-1) | Helped |
| Choose the box with the highest posterior probability of covering the scenario | MSSC · MSSC with time-dependent feedback | competitive ratio: 4 | Helped |
| Convert a time-dependent-feedback learner into a paid-feedback learner | MSSC · Buying information for MSSC | competitive ratio: 2α | Helped |
| Combine the greedy time-dependent-feedback algorithm with the buying-information reduction | MSSC · Buying information for MSSC | competitive ratio: 8 | Helped |
| Use an α-approximate rather than exact optimization value | DeterministicStopping · Super-martingale stopping with approximate optimization | competitive ratio: 2 -> 2α | Hurt |
| Use an α-approximate rather than exact optimization value | RandomizedStopping · Super-martingale stopping with approximate optimization | competitive ratio: e/(e-1) -> e/(e-1)α | Hurt |
| Stop when the current value falls below the round index (ablation) | Super-martingale stopping · Super-martingale stopping | competitive ratio: H_n | Hurt |
| Stop when the smallest value seen so far falls below the round index (ablation) | Super-martingale stopping · Super-martingale stopping | competitive ratio: Ω(n) | Hurt |
Closest papers by meaning
- Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search (ICML 2025 · similarity 0.87)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 2024 · similarity 0.87)
- Gradient Methods for Online DR-Submodular Maximization with Stochastic Long-Term Constraints (NeurIPS 2024 · similarity 0.86)
- Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates (NeurIPS 2024 · similarity 0.86)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.86)
- Learning-Augmented Online Bidding in Stochastic Settings (NeurIPS 2025 · similarity 0.86)
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.