Research map / Bandits and online learning / Online convex optimization and games
Trading-Off Payments and Accuracy in Online Classification with Paid Stochastic Experts
Dirk van der Hoeven, Ciara Pike-Burke, Hao Qiu, Nicolò Cesa-Bianchi
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 |
|---|---|---|---|
| Use LCB-GAPTRON rather than LCB, which pays one expert per round | Synthetic paid-expert classification · Synthetic linear and sigmoidal productivity | cumulative cost | Improved |
| Approximate joint payment optimization with independent per-expert optimization (ablation) | LCB-GAPTRON · Synthetic linear and sigmoidal productivity, K=5, N=5, T=10^4 | cumulative cost | No clear effect |
| Approximate joint payment optimization with iterative round-robin optimization (ablation) | LCB-GAPTRON · Synthetic linear and sigmoidal productivity, K=5, N=5, T=10^4 | cumulative cost | No clear effect |
| Use the single-expert LCB baseline instead of aggregating paid experts | Synthetic paid-expert classification · K=10, N=10, T=10^5, λ=10^-2 | cumulative cost | Mixed |
| Use LCB-GAPTRON rather than single-expert LCB | Synthetic paid-expert classification · K=10, N=10, λ=10^-3 or K=20, N=50, λ=10^-2 | cumulative cost | Improved |
Closest papers by meaning
- Online Linear Classification with Massart Noise (ICML 2025 · similarity 0.86)
- Online Classification with Predictions (NeurIPS 2024 · similarity 0.86)
- A Regret-Variance Trade-Off in Online Learning (NeurIPS 2022 · similarity 0.86)
- Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making (NeurIPS 2025 · similarity 0.85)
- Bandit and Delayed Feedback in Online Structured Prediction (NeurIPS 2025 · similarity 0.84)
- Stochastic Online Conformal Prediction with Semi-Bandit Feedback (ICML 2025 · similarity 0.84)
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.
