Research map / Probabilistic and scientific modeling / Bayesian optimization
Delayed Feedback in Kernel Bandits
Sattar Vakili, Danyal Ahmed, Alberto Bernacchia, Ciara Pike-Burke
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 BPE-Delay instead of GP-UCB-SDF | Kernel bandits with stochastic delays · Kernel bandits with stochastic delays | regret bound: \Oct(\Gamma_k(T)\sqrt{ T}+\mathbb{E}[\tau] \Gamma_k(T)) -> \Oct(\sqrt{\Gamma_k(T) T}+\mathbb{E}[\tau]) | Improved |
| Use BPE-Delay rather than GP-UCB-SDF | Kernel bandits with stochastic delays · Simulated objectives f1 and f2 | cumulative regret | Improved |
| Increase the Poisson delay parameter | BPE-Delay · Simulated objectives f1 and f2 | cumulative regret | Mixed |
| Increase the Poisson delay parameter | GP-UCB-SDF · Simulated objectives f1 and f2 | cumulative regret | Hurt |
| Use BPE-Delay instead of BPE | Delayed kernel bandits · Delayed feedback simulation | cumulative regret | Improved |
| Use the BPE-Delay regret analysis for linear kernels | Linear kernel bandits with stochastic delays · Linear kernel bandits | delay-related regret bound: d^{\frac{3}{2}} | Improved |
Closest papers by meaning
- Improved Regret for Bandit Convex Optimization with Delayed Feedback (NeurIPS 2024 · similarity 0.89)
- Online Nonsubmodular Optimization with Delayed Feedback in the Bandit Setting (AAAI 2025 · similarity 0.89)
- Near-Optimal Stochastic Linear Bandits with Delay (NeurIPS 2026 · similarity 0.88)
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization (NeurIPS 2026 · similarity 0.88)
- Bandit and Delayed Feedback in Online Structured Prediction (NeurIPS 2025 · similarity 0.88)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 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.
