Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Thompson Sampling for High-Dimensional Sparse Linear 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 VBTS with a sparsity-inducing prior instead of the compared methods | 2-armed contextual bandit on gravier Breast Carcinoma Data · gravier Breast Carcinoma Data | accuracy (%): 81.20 -> 81.88 | Helped |
| Approximate the posterior with Variational Bayes for Thompson sampling | Thompson sampling on Equicorrelated synthetic data · Equicorrelated synthetic data | mean execution time (seconds): 1344.39 -> 29.33; 1511.68 -> 29.33 | Helped |
| Approximate the posterior with Variational Bayes for Thompson sampling | Thompson sampling on Auto-regressive synthetic data · Auto-regressive synthetic data | mean execution time (seconds): 1346.46 -> 27.65; 1455.53 -> 27.65 | Helped |
| Use VBTS rather than the competing algorithms | Synthetic contextual bandits · Equicorrelated and auto-regressive designs, both coefficient setups | cumulative regret | Helped |
| Use VBTS rather than the compared methods | 2-armed contextual bandit on gravier Breast Carcinoma Data · gravier Breast Carcinoma Data | cumulative regret | Helped |
| Vary the tuning parameter from the constant setting to lambda_t = lambda_* sqrt(t), lambda_* in {0.2, 0.3, 0.4, 0.5} (ablation) | VBTS · Equicorrelated and auto-regressive synthetic data | cumulative regret | No clear effect |
| Increase lambda_* beyond the tested moderate range (ablation) | VBTS variational approximation · Synthetic data | numerical stability | Hurt |
Closest papers by meaning
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.93)
- $\mathtt{VITS}$ : Variational Inference Thompson Sampling for contextual bandits (ICML 2024 · similarity 0.91)
- High-dimensional Linear Bandits with Knapsacks (ICML 2024 · similarity 0.91)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.91)
- Thompson Sampling for Multi-Objective Linear Contextual Bandit (NeurIPS 2025 · similarity 0.91)
- Feel-Good Thompson Sampling for Contextual Dueling Bandits (ICML 2024 · similarity 0.90)
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.