Research map / Bandits and online learning / Multi-armed bandits
Dueling Bandits with Weak Regret
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 WS-W for weak regret | Dueling bandits · Simulated data, 50 arms | weak regret | Helped |
| Use WS-W for weak regret | Dueling bandits · Yelp Academic Dataset | utility-based weak regret | Helped |
| Use WS-S for strong regret | Dueling bandits · Sushi dataset and MSLR dataset | strong regret | Helped |
| Use WS-W rather than existing algorithms | Dueling bandits · Condorcet winner setting | expected cumulative weak regret: O(N^2) | Helped |
| Use WS-W rather than existing algorithms | Dueling bandits · Total order setting | expected cumulative weak regret: O(N log(N)) | Helped |
| Use WS-S rather than existing algorithms | Dueling bandits · Condorcet winner setting | expected cumulative strong regret: O(N^2 + N log(T)) | Helped |
Closest papers by meaning
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.95)
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 2024 · similarity 0.91)
- Borda Regret Minimization for Generalized Linear Dueling Bandits (ICML 2024 · similarity 0.91)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.89)
- Fusing Reward and Dueling Feedback in Stochastic Bandits (ICML 2025 · similarity 0.89)
- Bandits with Ranking Feedback (NeurIPS 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.