15 citations · 80 across the 26 of their papers we have counts for
10 papers · 1 filter
Incentivized Communication for Federated Bandits
Zhepei Wei, Chuanhao Li, Haifeng Xu +1
Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despi…
Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts
Chaoqi Wang, Ziyu Ye, Zhe Feng +2
Standard contextual bandit problem assumes that all the relevant contexts are observed before the algorithm chooses an arm. This modeling paradigm, while useful, often falls short…
Multi-Player Bandits Robust to Adversarial Collisions
Shivakumar Mahesh, Anshuka Rangi, Haifeng Xu +1
Motivated by cognitive radios, stochastic Multi-Player Multi-Armed Bandits has been extensively studied in recent years. In this setting, each player pulls an arm, and receives a r…
Learning Correlated Stackelberg Equilibrium in General-Sum Multi-Leader-Single-Follower Games
Yaolong Yu, Haifeng Xu, Haipeng Chen
Many real-world strategic games involve interactions between multiple players. We study a hierarchical multi-player game structure, where players with asymmetric roles can be separ…
Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
Anshuka Rangi, Haifeng Xu, Long Tran-Thanh +1
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards…
Incentivizing Exploration in Linear Bandits under Information Gap
Huazheng Wang, Haifeng Xu, Chuanhao Li +2
We study the problem of incentivizing exploration for myopic users in linear bandits, where the users tend to exploit arm with the highest predicted reward instead of exploring. In…
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification
Anshuka Rangi, Long Tran-Thanh, Haifeng Xu +1
We study bandit algorithms under data poisoning attacks in a bounded reward setting. We consider a strong attacker model in which the attacker can observe both the selected actions…
PAC-Learning for Strategic Classification
Ravi Sundaram, Anil Vullikanti, Haifeng Xu +1
The study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situati…
Collapsing Bandits and Their Application to Public Health Interventions
Aditya Mate, Jackson A. Killian, Haifeng Xu +2
We propose and study Collpasing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when…
The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation
Zhe Feng, David C. Parkes, Haifeng Xu
Motivated by economic applications such as recommender systems, we study the behavior of stochastic bandits algorithms under \emph{strategic behavior} conducted by rational actors,…