Research map / Bandits and online learning / Multi-armed bandits
Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
Vladimir Braverman, Chen Wang, Liudeng Wang, Samson Zhou
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 |
|---|---|---|---|
| increase memory from 0.05W to 0.3W (ablation) | eps-exploration algorithm · synthetic eps-exploration | error of returned arm: error exceeded 0.6 -> below 0.3 | Improved |
| use sliding-window algorithm instead of adapted streaming top-k baseline | eps-exploration · synthetic eps-exploration | error of returned arm: 0.6 -> 0.3 (error reduced by 50%) | Improved |
| increase memory from 0.05W to W (ablation) | regret minimization algorithm · synthetic regret minimization | total regret: decreased by more than 50% | Improved |
| increase memory of the baseline streaming algorithms (ablation) | top-k baseline · synthetic n=1000, W=50 | error and regret | No clear effect |
Closest papers by meaning
- Linear Streaming Bandit: Regret Minimization and Fixed-Budget Epsilon-Best Arm Identification (AAAI 2025 · similarity 0.89)
- Nearly Tight Bounds for Exploration in Streaming Multi-Armed Bandits with Known Optimality Gap (AAAI 2025 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.88)
- Leveraging (Biased) Information: Multi-armed Bandits with Offline Data (ICML 2024 · similarity 0.88)
- Bandits with Replenishable Knapsacks: the Best of both Worlds (ICLR 2024 · similarity 0.87)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.87)
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.
