Research map / Bandits and online learning / Contextual bandits and Thompson sampling
A Unifying Theory of Thompson Sampling for Continuous Risk-Averse 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 continuous and dominant risk functionals with ρ-MTS | Multinomial risk-averse bandits · Finite-alphabet bandits | asymptotic risk regret | Helped |
| Replace the slack mean-variance regret constant with the exact KL-based constant | Bernoulli-MVTS analysis · Bernoulli mean-variance bandits | regret bound: inv{(2min{(p_1-p_i)^2, (1 - γ - p_1 - p_i)^2})} -> K_inf^ρ(ν_k,r_1)^{-1} | Helped |
| Apply ρ-NPTS to continuous risk measures formed from linear combinations | ρ-NPTS · Three-arm Beta bandits; ρ₁ and ρ₂ | risk regret relative to lower bound | Helped |
| Use VaR, which is discontinuous under the stated metric | ρ-MTS guarantees · Finite-alphabet risk-averse bandits | availability of asymptotic regret guarantee | Hurt |
Closest papers by meaning
- Thompson Sampling Algorithms for Mean-Variance Bandits (ICML 2020 · similarity 0.92)
- On the Suboptimality of Thompson Sampling in High Dimensions (NeurIPS 2021 · similarity 0.91)
- Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits (NeurIPS 2025 · similarity 0.89)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.89)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 2024 · similarity 0.88)
- Constrained Linear Thompson Sampling (NeurIPS 2025 · 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.