Research map / Bandits and online learning / Online convex optimization and games
When Can We Track Significant Preference Shifts in Dueling Bandits?
Joe Suk, Arpit Agarwal
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 |
|---|---|---|---|
| METASWIFT instead of ANACONDA | METASWIFT · Non-stationary BTL, S=4 | dynamic regret: 5331 -> 3346 | Improved |
| METASWIFT instead of ANACONDA | METASWIFT · Stationary BTL, S=0 | dynamic regret: 4863 -> 3048 | Improved |
| Stationary-only Interleaved Filtering instead of METASWIFT, no changes | IF · Stationary BTL, S=0 | dynamic regret: 3048 -> 140 | Improved |
| Stationary-only IF used in an environment with 4 changes | IF · Non-stationary BTL, S=4 | dynamic regret: 140 -> 14142 | Hurt |
| METASWIFT with 4 changes vs none | METASWIFT · Geometric BTL | dynamic regret: 3048 -> 3346 | No clear effect |
| ANACONDA with 4 changes vs none | ANACONDA · Geometric BTL | dynamic regret: 4863 -> 5331 | No clear effect |
| METASWIFT instead of uniform random dueling | METASWIFT · Non-stationary BTL, S=4 | dynamic regret: 18684 -> 3346 | Improved |
Closest papers by meaning
- Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits (ICLR 2024 · similarity 0.89)
- On Weak Regret Analysis for Dueling Bandits (NeurIPS 2024 · similarity 0.89)
- Borda Regret Minimization for Generalized Linear Dueling Bandits (ICML 2024 · similarity 0.88)
- Tracking Most Significant Shifts in Infinite-Armed Bandits (ICML 2025 · similarity 0.88)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.88)
- Bandits with Ranking Feedback (NeurIPS 2024 · 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.
