no code implementations • 7 Feb 2024 • Safwan Hossain, Tonghan Wang, Tao Lin, YiLing Chen, David C. Parkes, Haifeng Xu
The core solution concept here is the Nash equilibrium of senders' signaling policies.
no code implementations • 7 Feb 2024 • Zhepei Wei, Chuanhao Li, Tianze Ren, Haifeng Xu, Hongning Wang
To enhance the efficiency and practicality of federated bandit learning, recent advances have introduced incentives to motivate communication among clients, where a client participates only when the incentive offered by the server outweighs its participation cost.
no code implementations • 15 Dec 2023 • Minbiao Han, Michael Albert, Haifeng Xu
We study a ubiquitous learning challenge in online principal-agent problems during which the principal learns the agent's private information from the agent's revealed preferences in historical interactions.
no code implementations • 27 Nov 2023 • Thomas Kleine Buening, Aadirupa Saha, Christos Dimitrakakis, Haifeng Xu
We study a strategic variant of the multi-armed bandit problem, which we coin the strategic click-bandit.
no code implementations • 4 Nov 2023 • Haolin Liu, Rajmohan Rajaraman, Ravi Sundaram, Anil Vullikanti, Omer Wasim, Haifeng Xu
In this paper, we initialize the study of sample complexity in opinion formation to solve this problem.
no code implementations • 27 Oct 2023 • Minbiao Han, Jonathan Light, Steven Xia, Sainyam Galhotra, Raul Castro Fernandez, Haifeng Xu
We envision that the synergy of our data and model discovery algorithm and pricing mechanism will be an important step towards building a new data-centric online market that serves ML users effectively.
no code implementations • 3 Feb 2023 • Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu
Content creators compete for exposure on recommendation platforms, and such strategic behavior leads to a dynamic shift over the content distribution.
no code implementations • 15 Nov 2022 • Shivakumar Mahesh, Anshuka Rangi, Haifeng Xu, Long Tran-Thanh
We provide the first decentralized and robust algorithm RESYNC for defenders whose performance deteriorates gracefully as $\tilde{O}(C)$ as the number of collisions $C$ from the attackers increases.
2 code implementations • 13 Nov 2022 • Stephanie Schoch, Haifeng Xu, Yangfeng Ji
Our theoretical analysis shows the proposed value function is (essentially) the unique function that satisfies two desirable properties for evaluating data values in classification.
no code implementations • 22 Oct 2022 • Yaolong Yu, Haifeng Xu, Haipeng Chen
Many real-world strategic games involve interactions between multiple players.
no code implementations • 29 Aug 2022 • Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i. e., the manipulation of \emph{reward} and \emph{action}.
no code implementations • 2 Jun 2022 • Ashwinkumar Badanidiyuru, Zhe Feng, Tianxi Li, Haifeng Xu
Incrementality, which is used to measure the causal effect of showing an ad to a potential customer (e. g. a user in an internet platform) versus not, is a central object for advertisers in online advertising platforms.
no code implementations • 22 Feb 2022 • Jibang Wu, Zixuan Zhang, Zhe Feng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan, Haifeng Xu
This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs), where a sender, with informational advantage, seeks to persuade a stream of myopic receivers to take actions that maximizes the sender's cumulative utilities in a finite horizon Markovian environment with varying prior and utility functions.
no code implementations • 12 Feb 2022 • Yiding Feng, Wei Tang, Haifeng Xu
For each user with her own private preference and belief, the platform commits to a recommendation strategy to utilize his information advantage on the product state to persuade the self-interested user to follow the recommendation.
no code implementations • 3 Feb 2022 • Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu
In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from their experience about previously consumed items.
1 code implementation • NeurIPS 2021 • Sijun Tan, Jibang Wu, Xiaohui Bei, Haifeng Xu
Peer review systems such as conference paper review often suffer from the issue of miscalibration.
no code implementations • 10 Nov 2021 • Jibang Wu, Haifeng Xu, Fan Yao
Under the uncoupled learning setup, the last-iterate convergence guarantee towards Nash equilibrium is shown to be impossible in many games.
1 code implementation • NeurIPS 2021 • Chengshuai Shi, Haifeng Xu, Wei Xiong, Cong Shen
In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications.
1 code implementation • 25 Oct 2021 • Sijun Tan, Jibang Wu, Xiaohui Bei, Haifeng Xu
Peer review systems such as conference paper review often suffer from the issue of miscalibration.
no code implementations • 18 Oct 2021 • Huazheng Wang, Haifeng Xu, Hongning Wang
We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm.
no code implementations • 6 Oct 2021 • Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu
We propose a new problem setting to study the sequential interactions between a recommender system and a user.
no code implementations • 25 Sep 2021 • Chenghan Zhou, Thanh H. Nguyen, Haifeng Xu
This paper initiates the algorithmic information design of both \emph{public} and \emph{private} signaling in a fundamental class of games with negative externalities, i. e., singleton congestion games, with wide application in today's digital economy, machine scheduling, routing, etc.
1 code implementation • 9 Jun 2021 • Quinlan Dawkins, Tianxi Li, Haifeng Xu
Diffusion source identification on networks is a problem of fundamental importance in a broad class of applications, including rumor controlling and virus identification.
no code implementations • 8 Apr 2021 • Huazheng Wang, Haifeng Xu, Chuanhao Li, Zhiyuan Liu, Hongning Wang
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.
no code implementations • 19 Feb 2021 • You Zu, Krishnamurthy Iyer, Haifeng Xu
We study a repeated persuasion setting between a sender and a receiver, where at each time $t$, the sender observes a payoff-relevant state drawn independently and identically from an unknown prior distribution, and shares state information with the receiver, who then myopically chooses an action.
no code implementations • 15 Feb 2021 • Anshuka Rangi, Long Tran-Thanh, Haifeng Xu, Massimo Franceschetti
In particular, for the case of unlimited verifications, we show that with $O(\log T)$ expected number of verifications, a simple modified version of the ETC type bandit algorithm can restore the order optimal $O(\log T)$ regret irrespective of the amount of contamination used by the attacker.
no code implementations • 6 Dec 2020 • Ravi Sundaram, Anil Vullikanti, Haifeng Xu, Fan Yao
In this paper, we generalize both of these through a unified framework for strategic classification, and introduce the notion of strategic VC-dimension (SVC) to capture the PAC-learnability in our general strategic setup.
1 code implementation • NeurIPS 2020 • Aditya Mate, Jackson Killian, Haifeng Xu, Andrew Perrault, Milind Tambe
Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable.
no code implementations • 5 Jul 2020 • Aditya Mate, Jackson A. Killian, Haifeng Xu, Andrew Perrault, Milind Tambe
(ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed-form.
no code implementations • ICML 2020 • Zhe Feng, David C. Parkes, Haifeng Xu
We prove that all three algorithms achieve a regret upper bound $\mathcal{O}(\max \{ B, K\ln T\})$ where $B$ is the total budget across arms, $K$ is the total number of arms and $T$ is length of the time horizon.
no code implementations • 29 Apr 2019 • Haifeng Xu, Mariana Medina-Sanchez, Daniel R. Brison, Richard J. Edmondson, Stephen S. Taylor, Louisa Nelson, Kang Zeng, Steven Bagley, Carla Ribeiro, Lina P. Restrepo, Elkin Lucena, Christine K. Schmidt, Oliver G. Schmidt
Here, we successfully load human sperm with a chemotherapeutic drug and perform treatment of relevant 3D cervical cancer and patient-representative 3D ovarian cancer cell cultures, resulting in strong anti-cancer effects.
no code implementations • 11 Mar 2017 • Haifeng Xu, Milind Tambe, Shaddin Dughmi, Venil Loyd Noronha
To mitigate this issue, we propose to design entropy-maximizing defending strategies for spatio-temporal security games, which frequently suffer from CoC.
no code implementations • 30 Jan 2016 • Amulya Yadav, Hau Chan, Albert Jiang, Haifeng Xu, Eric Rice, Milind Tambe
This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth.
no code implementations • 23 Apr 2015 • Haifeng Xu, Albert X. Jiang, Arunesh Sinha, Zinovi Rabinovich, Shaddin Dughmi, Milind Tambe
Our experiments confirm the necessity of handling information leakage and the advantage of our algorithms.