In this paper we study a multi-arm bandit problem in which the quality of each arm is measured by the Conditional Value at Risk (CVaR) at some level alpha of the reward …
Even when unable to run experiments, practitioners can evaluate prospective policies, using previously logged data. However, while the bandits literature has adopted a diverse set of …
Abstract Conditional Value-at-Risk (CVaR) is a widely used risk metric in applications such as finance. We derive concentration bounds for CVaR estimates, considering separately the …
S Bhatt, G Fang, P Li… - … Conference on Machine …, 2022 - proceedings.mlr.press
In this paper, we extend the remarkable M-estimator of Catoni\citep {Cat12} to situations where the variance is infinite. In particular, given a sequence of iid random variables $\{X_i\} …
Autonomous systems are increasingly used in highly variable and uncertain environments giving rise to the pressing need to consider risk in both the synthesis and verification of …
J Huang, Y Dai, L Huang - international conference on …, 2022 - proceedings.mlr.press
In this paper, we generalize the concept of heavy-tailed multi-armed bandits to adversarial environments, and develop robust best-of-both-worlds algorithms for heavy-tailed multi …
H Wang, Y Yang, E Wang, W Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Mobile Crowdsensing (MCS) is a promising paradigm that recruits users to cooperatively perform a sensing task. When recruiting users, existing works mainly focus on selecting a …
K Lee, H Yang, S Lim, S Oh - Advances in Neural …, 2020 - proceedings.neurips.cc
Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards Page 1 Optimal Algorithms for Stochastic Multi-Armed Bandits with Heavy Tailed Rewards Kyungjae Lee …
S Agrawal, WM Koolen… - Advances in Neural …, 2021 - proceedings.neurips.cc
Conditional value-at-risk (CVaR) and value-at-risk (VaR) are popular tail-risk measures in finance and insurance industries as well as in highly reliable, safety-critical uncertain …