Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Thompson Sampling Algorithms for Mean-Variance 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 MVTS instead of MV-LCB | Gaussian mean-variance bandits · Gaussian mean-variance bandits | expected regret | Helped |
| Use VTS instead of the other compared algorithms | Gaussian mean-variance bandits with ρ = 10^{-3} · Gaussian mean-variance bandits, ρ = 10^{-3} | expected regret | Helped |
| Use MTS instead of the other compared algorithms | Gaussian mean-variance bandits with ρ = 1000 · Gaussian mean-variance bandits, ρ = 1000 | expected regret | Helped |
| Use MTS, VTS, or MVTS instead of MV-LCB | Gaussian mean-variance bandits with ρ = 1 · Gaussian mean-variance bandits, ρ = 1 | expected regret | Helped |
| Use MVTS instead of MV-LCB | Gaussian mean-variance bandits across risk tolerances · Gaussian mean-variance bandits, ρ ∈ [10^{-3},1000] | expected regret | Helped |
| Use BMVTS instead of the LCB-based algorithm | Bernoulli mean-variance bandits · Bernoulli mean-variance bandits, ρ ∈ (0,1) | expected regret | Helped |
| Combine Thompson sampling over the mean and precision in MVTS rather than selecting a mean-focused or variance-focused algorithm | Gaussian mean-variance bandits · Gaussian mean-variance bandits across risk tolerances | expected regret | Mixed |
| Use MTS in place of the unified MVTS method | Gaussian mean-variance bandits · Gaussian mean-variance bandits, ρ = 10^{-3} | expected regret | Hurt |
| Use VTS in place of the unified MVTS method | Gaussian mean-variance bandits · Gaussian mean-variance bandits, ρ = 1000 | expected regret | Hurt |
Closest papers by meaning
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.91)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.91)
- Forced Exploration in Bandit Problems (AAAI 2024 · similarity 0.90)
- Constrained Linear Thompson Sampling (NeurIPS 2025 · similarity 0.89)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 2024 · similarity 0.89)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 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.