Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Neural Contextual Bandits with Deep Representation and Shallow 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 deep representation with UCB exploration only in the last layer instead of exploration over the full network | Neural contextual bandits · Statlog | cumulative regret | Helped |
| Use deep representation with UCB exploration only in the last layer instead of exploration over the full network | Neural contextual bandits · Magic | cumulative regret | Helped |
| Use deep representation with UCB exploration only in the last layer instead of exploration over the full network | Neural contextual bandits · Covertype | cumulative regret | Helped |
| Use a learned neural representation instead of raw features | LinUCB · Statlog, Magic, Covertype | cumulative regret | Helped |
| Use deep representation with UCB exploration in the last layer instead of Bayesian linear posterior sampling | Neural-Linear · Statlog, Magic, Covertype | cumulative regret | Helped |
| Restrict UCB exploration to the last layer | NeuralUCB · Statlog | runtime (seconds): 19,028 -> 783 | Helped |
| Restrict UCB exploration to the last layer | NeuralUCB · Magic | runtime (seconds): 18,579 -> 7,263 | Helped |
| Restrict UCB exploration to the last layer | NeuralUCB · Covertype | runtime (seconds): 11,941 -> 3,443 | Helped |
Closest papers by meaning
- Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits (ICML 2024 · similarity 0.89)
- Robust Neural Contextual Bandit against Adversarial Corruptions (NeurIPS 2024 · similarity 0.88)
- High Probability Bound for Cross-Learning Contextual Bandits with Unknown Context Distributions (ICML 2025 · similarity 0.88)
- Exploration via Feature Perturbation in Contextual Bandits (NeurIPS 2025 · similarity 0.88)
- Stochastic Bandits with ReLU Neural Networks (ICML 2024 · similarity 0.87)
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (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.