Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Neural Contextual Bandits with UCB-based Exploration
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 NeuralUCB's UCB exploration instead of epsilon-greedy exploration (ablation) | Neural network contextual bandits · Synthetic and real-world contextual bandit tasks | cumulative regret | Helped |
| Use the full neural network instead of the fixed NTK feature mapping (ablation) | NeuralUCB · Synthetic and real-world contextual bandit tasks | cumulative regret | Helped |
| Use neural network representations rather than a linear representation | Contextual bandit algorithms · Synthetic and real-world tasks with nonlinear reward functions | cumulative regret | Helped |
| Use a flexible neural network rather than a sigmoid link over a linear function | Contextual bandit algorithms · Synthetic and real-world tasks | cumulative regret | Mixed |
| Use neural network features rather than a predefined RBF kernel | NeuralUCB · Synthetic and real-world contextual bandit tasks | cumulative regret | Helped |
| Use a single neural network rather than an ensemble of bootstrapped neural networks | NeuralUCB · Real-world contextual bandit tasks | computational cost | Helped |
Closest papers by meaning
- Learning Neural Contextual Bandits through Perturbed Rewards (ICLR 2022 · similarity 0.94)
- Exploration via Feature Perturbation in Contextual Bandits (NeurIPS 2025 · similarity 0.91)
- Robust Neural Contextual Bandit against Adversarial Corruptions (NeurIPS 2024 · similarity 0.90)
- High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions (ICML 2025 · similarity 0.89)
- Contextual Bandits with Online Neural Regression (ICLR 2024 · similarity 0.89)
- Neural Dueling Bandits: Preference-Based Optimization with Human Feedback (ICLR 2025 · similarity 0.89)
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.