中文
相关论文

相关论文: Risk averse non-stationary multi-armed bandits

200 篇论文

We study MNL bandits, which is a variant of the traditional multi-armed bandit problem, under risk criteria. Unlike the ordinary expected revenue, risk criteria are more general goals widely used in industries and bussiness. We design…

机器学习 · 计算机科学 2021-03-17 Guangyu Xi , Chao Tao , Yuan Zhou

We present the conditional value-at-risk (CVaR) in the context of Markov chains and Markov decision processes with reachability and mean-payoff objectives. CVaR quantifies risk by means of the expectation of the worst p-quantile. As such it…

计算机科学中的逻辑 · 计算机科学 2018-05-09 Jan Křetínský , Tobias Meggendorfer

We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random covariate. The goal is to maximize cumulative expected reward.…

统计理论 · 数学 2010-03-09 Philippe Rigollet , Assaf Zeevi

This paper studies the optimization of Markov decision processes (MDPs) from a risk-seeking perspective, where the risk is measured by conditional value-at-risk (CVaR). The objective is to find a policy that maximizes the long-run CVaR of…

最优化与控制 · 数学 2023-12-05 Li Xia , Zhihui Yu , Peter W. Glynn

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this…

机器学习 · 计算机科学 2020-03-09 Aldo Pacchiano , Heinrich Jiang , Michael I. Jordan

We consider a class of risk-averse submodular maximization problems (RASM) where the objective is the conditional value-at-risk (CVaR) of a random nondecreasing submodular function at a given risk level. We propose valid inequalities and an…

最优化与控制 · 数学 2020-04-17 Hao-Hsiang Wu , Simge Kucukyavuz

We consider the problem of risk-sensitive motion planning in the presence of randomly moving obstacles. To this end, we adopt a model predictive control (MPC) scheme and pose the obstacle avoidance constraint in the MPC problem as a…

系统与控制 · 电气工程与系统科学 2021-07-20 Anushri Dixit , Mohamadreza Ahmadi , Joel W. Burdick

The stochastic multi-armed bandit setting has been recently studied in the non-stationary regime, where the mean payoff of each action is a non-decreasing function of the number of rounds passed since it was last played. This model captures…

机器学习 · 计算机科学 2022-10-13 Orestis Papadigenopoulos , Constantine Caramanis , Sanjay Shakkottai

Multi-armed bandits (MAB) model sequential decision making problems, in which a learner sequentially chooses arms with unknown reward distributions in order to maximize its cumulative reward. Most of the prior work on MAB assumes that the…

机器学习 · 计算机科学 2018-03-22 Onur Atan , Cem Tekin , Mihaela van der Schaar

We consider the classical multi-armed bandit problem with Markovian rewards. When played an arm changes its state in a Markovian fashion while it remains frozen when not played. The player receives a state-dependent reward each time it…

最优化与控制 · 数学 2022-11-15 Cem Tekin , Mingyan Liu

We consider bandit problems involving a large (possibly infinite) collection of arms, in which the expected reward of each arm is a linear function of an $r$-dimensional random vector $\mathbf{Z} \in \mathbb{R}^r$, where $r \geq 2$. The…

机器学习 · 计算机科学 2010-02-24 Paat Rusmevichientong , John N. Tsitsiklis

Non-stationary parametric bandits have attracted much attention recently. There are three principled ways to deal with non-stationarity, including sliding-window, weighted, and restart strategies. As many non-stationary environments exhibit…

机器学习 · 计算机科学 2023-06-08 Jing Wang , Peng Zhao , Zhi-Hua Zhou

Contextual multi-armed bandit (MAB) algorithms have been shown promising for maximizing cumulative rewards in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health.…

机器学习 · 统计学 2019-02-01 Gi-Soo Kim , Myunghee Cho Paik

Value at Risk (VaR) and Conditional Value at Risk (CVaR) have become the most popular measures of market risk in Financial and Insurance fields. However, the estimation of both risk measures is challenging, because it requires the knowledge…

统计方法学 · 统计学 2024-10-17 Jacinto Martín , M. Isabel Parra , Eva L. Sanjuán , Mario M. Pizarro

This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant. We prove generalised concentration bounds…

机器学习 · 计算机科学 2022-04-19 Joel Q. L. Chang , Vincent Y. F. Tan

In restless bandits, a central agent is tasked with optimally distributing limited resources across several bandits (arms), with each arm being a Markov decision process. In this work, we generalize the traditional restless bandits problem…

机器学习 · 计算机科学 2026-02-20 Nima Akbarzadeh , Yossiri Adulyasak , Erick Delage

We study a problem of information gathering in a social network with dynamically available sources and time varying quality of information. We formulate this problem as a restless multi-armed bandit (RMAB). In this problem, information…

系统与控制 · 计算机科学 2018-01-22 Varun Mehta , Rahul Meshram , Kesav Kaza , S. N. Merchant

Conditional Value at Risk (CVaR) is a family of "coherent risk measures" which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garnering increasing interest in machine learning, e.g., as an…

机器学习 · 计算机科学 2020-11-17 Zakaria Mhammedi , Benjamin Guedj , Robert C. Williamson

This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets as sub-level sets of the solution to a non-standard optimal…

系统与控制 · 电气工程与系统科学 2022-06-28 Margaret P. Chapman , Riccardo Bonalli , Kevin M. Smith , Insoon Yang , Marco Pavone , Claire J. Tomlin

This work proposes a secure and dynamic VM allocation strategy for multi-tenant distributed systems using the Thompson sampling approach. The method proves more effective and secure compared to epsilon-greedy and upper confidence bound…

分布式、并行与集群计算 · 计算机科学 2024-10-08 Pravin Patil , Geetanjali Kale , Tanmay Karmarkar , Ruturaj Ghatage