Research map / Bandits and online learning / Online convex optimization and games
Combinatorial Bandits with Relative Feedback
Aadirupa Saha, Aditya Gopalan
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 MM (max-min set building with rank-ordered feedback) instead of Battling-Duel | MM · MNL environments g1,g4,arith,geo,har (k=10, m=5) | Winner-regret | Improved |
| use MM instead of Self-Sparring with Thompson Sampling | MM · MNL environments g1,g4,arith,geo,har (k=10, m=5) | Winner-regret | Improved |
| use Rec-MM instead of modified Sp-TS | Rec-MM · MNL environments (k=10) | Top-k-regret | Improved |
| increase size of rank-ordered feedback m with fixed k=40 | MM · arithb and geob (n=50) | Winner-regret and Top-k-regret | Improved |
| larger gap between best items (easier instance g4 vs har) | Rec-MM · g4 vs har | convergence speed of Top-k-regret | Improved |
Closest papers by meaning
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.91)
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.89)
- Bandits with Ranking Feedback (NeurIPS 2024 · similarity 0.89)
- Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits (NeurIPS 2024 · similarity 0.88)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 2024 · similarity 0.88)
- Combinatorial Reinforcement Learning with Preference Feedback (ICML 2025 · similarity 0.88)
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.
