# Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs

arXiv: https://arxiv.org/abs/2206.12463 · HTML: https://mlsanity.com/paper/2206.12463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 24 Jun 2022.

## Builds on (most cited first, 11 of 11)

- [Expectation Propagation for approximate Bayesian inference](https://mlsanity.com/paper/1301.2294/) (2013)
- [Thompson Sampling Algorithms for Mean-Variance Bandits](https://mlsanity.com/paper/2002.00232/) (2020)
- [Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits](https://mlsanity.com/paper/1401.1123/) (2014)
- [Optimal Thompson Sampling strategies for support-aware CVaR bandits](https://mlsanity.com/paper/2012.05754/) (2020)
- [Variational Bayes under Model Misspecification](https://mlsanity.com/paper/1905.10859/) (2019)
- [Langevin Monte Carlo for Contextual Bandits](https://mlsanity.com/paper/2206.11254/) (2022)
- [Risk-Averse Multi-Armed Bandit Problems under Mean-Variance Measure](https://mlsanity.com/paper/1604.05257/) (2016)
- [Generalized Risk-Aversion in Stochastic Multi-Armed Bandits](https://mlsanity.com/paper/1405.0833/) (2014)
- [Risk-Constrained Thompson Sampling for CVaR Bandits](https://mlsanity.com/paper/2011.08046/) (2020)
- [A practical tutorial on Variational Bayes](https://mlsanity.com/paper/2103.01327/) (2021)
- [Thompson Sampling for Gaussian Entropic Risk Bandits](https://mlsanity.com/paper/2105.06960/) (2021)

## Built on by (most cited first, 1 of 1)

- [Online Bayesian Risk-Averse Reinforcement Learning](https://mlsanity.com/paper/2509.14077/) (2025)

## Abstract (arXiv)

In this paper we consider the contextual multi-armed bandit problem for linear payoffs under a risk-averse criterion. At each round, contexts are revealed for each arm, and the decision maker chooses one arm to pull and receives the corresponding reward. In particular, we consider mean-variance as the risk criterion, and the best arm is the one with the largest mean-variance reward. We apply the Thompson Sampling algorithm for the disjoint model, and provide a comprehensive regret analysis for a variant of the proposed algorithm. For T rounds, K actions, and d-dimensional feature vectors, we prove a regret bound of O((1+ρ+frac1ρ) dln T ln fracKδ√d K T1+2ε ln fracKδ frac1ε) that holds with probability 1-δ under the mean-variance criterion with risk tolerance ρ, for any 0<ε<frac12, 0<δ<1. The empirical performance of our proposed algorithms is demonstrated via a portfolio selection problem.