Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions
Youngmin Oh
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 RCDP-UCB unified clipping weight (corruption + delay budget) instead of RCDB weighting | RCDB · Linear dueling bandit without post-serving contexts (strategic and stochastic delays) | cumulative regret | Improved |
| learn post-serving contexts with an MLP and use them in the utility model | RCDP-UCB · Sinusoidal, Polynomial, Absolute mappings; strategic and stochastic delay | cumulative regret | Improved |
| give baselines post-serving context (+PS) via the same learned mapping instead of pre-serving only (ablation) | RCDB, ColSTIM, MaxInP, MaxPairUCB · Figure 2 (+PS baselines) vs Figure 3 | cumulative regret | No clear effect |
Closest papers by meaning
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.91)
- Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification (NeurIPS 2024 · similarity 0.90)
- Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays (NeurIPS 2026 · similarity 0.89)
- Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback (ICML 2025 · similarity 0.88)
- Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback (NeurIPS 2025 · similarity 0.88)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 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.
