Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Neural Thompson Sampling
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 NeuralTS instead of NeuralUCB | contextual bandit classification · Adult | total regret: 2092.5 ±48.0 vs 2061.8 ±42.8 | Hurt |
| Use NeuralTS instead of NeuralUCB | contextual bandit classification · Covertype | total regret: 3012.1 ±87.0 -> 2999.1 ±74.3 | Helped |
| Use NeuralTS instead of NeuralUCB | contextual bandit classification · Magic Telescope | total regret: 2033.0 ±48.6 -> 2037.4 ±61.3 | Hurt |
| Use NeuralTS instead of BootstrapNN | contextual bandit classification · MNIST | total regret: 1765.6 ±321.1 -> 1583.4 ±198.5 | Helped |
| Use NeuralTS instead of BootstrapNN | contextual bandit classification · Mushroom | total regret: 132.3 ±8.6 -> 115.0 ±35.8 | Helped |
| Use NeuralTS instead of Kernel UCB | contextual bandit classification · Shuttle | total regret: 166.5 ±39.4 -> 232.0 ±149.5 | Hurt |
| Use NeuralTS rather than NeuralUCB as reward delays increase | contextual bandits with delayed rewards · UCI datasets and MNIST | total regret | Helped |
Closest papers by meaning
- Combinatorial Neural Bandits (ICML 2023 · similarity 0.92)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.91)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.89)
- Thompson Sampling for Multi-Objective Linear Contextual Bandit (NeurIPS 2025 · similarity 0.89)
- Feel-Good Thompson Sampling for Contextual Dueling Bandits (ICML 2024 · similarity 0.88)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 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.