Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Provably and Practically Efficient Neural Contextual Bandits
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 NeuralGCB instead of LinUCB, NeuralUCB, NeuralTS, or SupNeuralUCB | Neural contextual bandits · Synthetic datasets and Mushroom | cumulative regret | Helped |
| Use σ₂ instead of σ₁ (ReLU) activation | Neural contextual bandit algorithms · Synthetic datasets and Mushroom | cumulative regret | Helped |
| Batch neural-network retraining rather than retraining sequentially | NeuralGCB and NeuralUCB · Synthetic functions and Mushroom | running time | Helped |
| Use NeuralGCB rather than Batched NeuralUCB | Batched neural contextual bandits · Synthetic functions and Mushroom | cumulative regret | Helped |
| Extend the NeuralGCB analysis and algorithm to smooth activations rather than only ReLU | Neural contextual bandits · Theoretical regret | regret | Helped |
Closest papers by meaning
- Learning Neural Contextual Bandits through Perturbed Rewards (ICLR 2022 · similarity 0.94)
- Neural Contextual Bandits with UCB-based Exploration (ICML 2020 · similarity 0.91)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.90)
- Second Order Bounds for Contextual Bandits with Function Approximation (ICLR 2025 · similarity 0.89)
- Exploration via Feature Perturbation in Contextual Bandits (NeurIPS 2025 · similarity 0.89)
- Contextual Bandits with Online Neural Regression (ICLR 2024 · 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.