20,110 Hits in 6.9 sec

Optimality and Stability in Federated Learning: A Game-theoretic Approach [article]

Kate Donahue, Jon Kleinberg
2021 arXiv   pre-print
One branch of this research has taken a game-theoretic approach, and in particular, prior work has viewed federated learning as a hedonic game, where error-minimizing players arrange themselves into federating  ...  In this work, we motivate and define a notion of optimality given by the average error rates among federating agents (players).  ...  A game-theoretic approach to coalition formation in fog provider federations. 2018 Third International Conference on Fog and Mobile Edge Computing (FMEC), pages 123-130, 2018.  ... 
arXiv:2106.09580v1 fatcat:fcnrs62tbfbivo6jceyzdby66m

Empirical and Normative Economics: A Game Theoretic Approach

Frederick Betz
2020 Theoretical Economics Letters  
In this research, we formulate a "game-theoretic approach" to include financial regulation as an explicit part of the model of a financial market.  ...  Future research direction from this game approach can extend the traditional "endogenous economic theory of markets" into an empirical modeling technique-which can ground economic theory in the real history  ...  (It will provide a historical case for seeing how a financial crisis can be analyzed in a new approach of game-theoretic models).  ... 
doi:10.4236/tel.2020.103042 fatcat:jnomwyez7rb77bdxxdv6auchxu

A Game Theoretical Approach for Solving Winner Determination Problems

Chen-Kun Tsung, Hann-Jang Ho, Sing-Ling Lee
2014 Journal of Applied Mathematics  
In this paper, we apply three concepts of the game theory to design an approximation algorithm: the stability of the Nash equilibrium, the self-learning of the evolutionary game, and the mistake making  ...  Determining the winners in combinatorial auctions to maximize the auctioneer's revenue is an NP-complete problem. Computing an optimal solution requires huge computation time in some instances.  ...  Acknowledgments This work was supported in part by Taiwan NSC under Grant no. NSC 102-2221-E-274-004 and NSC 102-2221-E-194-054-.  ... 
doi:10.1155/2014/845071 fatcat:2tddov4f4ndr3oq3kqgj6ggtyi

A Game-theoretic Approach Towards Collaborative Coded Computation Offloading [article]

Jer Shyuan Ng, Wei Yang Bryan Lim, Zehui Xiong, Dusit Niyato, Cyril Leung, Dong In Kim, Junshan Zhang, Qiang Yang
2021 arXiv   pre-print
In this paper, we propose a tractable two-level game-theoretic approach to incentivize the edge servers to complete the CDC tasks.  ...  Coded distributed computing (CDC) has emerged as a promising approach because it enables computation tasks to be carried out in a distributed manner while mitigating straggler effects, which often account  ...  . data mining, especially in transfer learning, automated planning, federated learning and case-based reasoning.  ... 
arXiv:2102.08667v1 fatcat:3rd5m5nctfeldnxkcqrluydmiu

Efficient MAC in cognitive radio systems: A game-theoretic approach

Mark Felegyhazi, Mario Cagalj, Jean-Pierre Hubaux
2009 IEEE Transactions on Wireless Communications  
Both problems are studied in a game-theoretic setting, where devices aim to selfishly maximize their share of the available bandwidth.  ...  For the second problem, we design a game such that it admits a unique Nash equilibrium that is is both fair and Pareto-optimal.  ...  A. Convergence in the CA Game In Section V, we presented a set of theoretical results to identify Nash equilibria in the CA game and we showed that they are efficient.  ... 
doi:10.1109/twc.2009.080284 fatcat:p73aovx4enh2lisq4bzxpsa2o4

Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach [article]

Hamid Shiri, Jihong Park, Mehdi Bennis
2019 arXiv   pre-print
Numerical evaluations validate that the proposed ML aided MFG theoretic algorithm, referred to as MFG learning control, is effective in collision avoidance with low communication energy and acceptable  ...  We tackle this problem by exploiting a mean-field game (MFG) theoretic control method that requires the UAV state exchanges only once at the initial source.  ...  While effective, MFG theoretic approaches are computationally expensive due to solving both HJB and FPK equations, particularly with multi-dimensional states [6] , limiting their adoption for real-time  ... 
arXiv:1905.04152v1 fatcat:vfgqcfuvcnfh3kdvuyenuan4si

On influence, stable behavior, and the most influential individuals in networks: A game-theoretic approach

Mohammad T. Irfan, Luis E. Ortiz
2014 Artificial Intelligence  
We propose influence games as a game-theoretic model of the behavior of a large but finite networked population.  ...  We introduce a new approach to the study of influence in strategic settings where the action of an individual depends on that of others in a network-structured way.  ...  First and foremost, we illustrated our approach to influence in a new setting-the U.S. Supreme Court rulings. Given the U.S.  ... 
doi:10.1016/j.artint.2014.06.004 fatcat:2ua6wdxaxvfgnbrdtjxqd27oau

Reliable Distributed Computing for Metaverse: A Hierarchical Game-Theoretic Approach [article]

Yuna Jiang, Jiawen Kang, Dusit Niyato, Xiaohu Ge, Zehui Xiong, Chunyan Miao, Xuemin Shen
2022 arXiv   pre-print
Therefore, this paper introduces a hierarchical game-theoretic CDC framework for the metaverse services, especially for the vehicular metaverse.  ...  Specifically, in the upper layer, a miner coalition formation game is formulated based on a reputation metric to select reliable workers.  ...  In order to realize reliable and sustainable CDC in the vehicular metaverse, we adopt a hierarchical game-theoretic approach based on coalition formation and Stackelberg game.  ... 
arXiv:2111.10548v2 fatcat:ab34ryxjmnay5chjro2qd2tymq

Massive Autonomous UAV Path Planning: A Neural Network Based Mean-Field Game Theoretic Approach

Hamid Shiri, Jihong Park, Mehdi Bennis
2019 2019 IEEE Global Communications Conference (GLOBECOM)  
Numerical evaluations validate that the proposed ML aided MFG theoretic algorithm, referred to as MFG learning control, is effective in collision avoidance with low communication energy and acceptable  ...  We tackle this problem by exploiting a mean-field game (MFG) theoretic control method that requires the UAV state exchanges only once at the initial source.  ...  Collaborative HJB and FPK model training across UAVs via federated learning frameworks [17] could thus be an interesting topic for future work. research was supported in part by Academy of Finland (Grant  ... 
doi:10.1109/globecom38437.2019.9013181 dblp:conf/globecom/ShiriPB19 fatcat:5m5zy76vfzc6dbyeblv4gq32ku

Implementation of a multi-agent environmental regulation strategy under Chinese fiscal decentralization: An evolutionary game theoretical approach

Ke Jiang, Daming You, Ryan Merrill, Zhendong Li
2019 Journal of Cleaner Production  
First, the selection of environmental strategies manifest in a dynamic process of constant adjustment and optimization.  ...  A numerical example serves to verify the theoretical results and support four key insights.  ...  Acknowledgment This research is supported by the National Natural Science Foundation of China (Nos.71573283, 71701217), a Grant from China Scholarship Council (No. 201606370071), and the Fundamental Research  ... 
doi:10.1016/j.jclepro.2018.12.252 fatcat:sqcfjmokevbapjwni5niyqi4xu

Incentive Mechanism Design for Federated Learning: Hedonic Game Approach [article]

Cengis Hasan
2021 arXiv   pre-print
We formulate the problem as a non-cooperative game and prove the existence of a potential game.  ...  Incentive mechanism design is crucial for enabling federated learning. We deal with clustering problem of agents contributing to federated learning setting.  ...  can provide a theoretical guarantee for users' privacy in federated learning participation.  ... 
arXiv:2101.09673v2 fatcat:adnu5zs4enaltmnt62ewe62spy

Social Welfare Maximization in Cross-Silo Federated Learning [article]

Jianan Chen, Qin Hu, Honglu Jiang
2022 arXiv   pre-print
In this paper, we model the interactions among organizations in cross-silo FL as a public goods game for the first time and theoretically prove that there exists a social dilemma where the maximum social  ...  As one of the typical settings of Federated Learning (FL), cross-silo FL allows organizations to jointly train an optimal Machine Learning (ML) model.  ...  INTRODUCTION In Federated Learning (FL), clients cooperatively train a Machine Learning (ML) model with their decentralized datasets under the coordination of a central server [1] .  ... 
arXiv:2202.09044v2 fatcat:bzhteelrunhstno3u5wjfya5oi

Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective [article]

Xuezhen Tu, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Yang Zhang, Juan Li
2021 arXiv   pre-print
In this paper, we provide a comprehensive review for the economic and game theoretic approaches proposed in the literature to design various schemes for stimulating data owners to participate in FL training  ...  Federated learning (FL) becomes popular and has shown great potentials in training large-scale machine learning (ML) models without exposing the owners' raw data.  ...  In [85] and [86] , the authors considered a federated learning training service market.  ... 
arXiv:2111.11850v1 fatcat:24xqnqiqtbh2hdn6lnkdkctqii

FL Games: A federated learning framework for distribution shifts [article]

Sharut Gupta and Kartik Ahuja and Mohammad Havaei and Niladri Chatterjee and Yoshua Bengio
2022 arXiv   pre-print
We propose FL Games, a game-theoretic framework for federated learning for learning causal features that are invariant across clients.  ...  Federated learning aims to train predictive models for data that is distributed across clients, under the orchestration of a server.  ...  In this study, we introduce Federated Learning Games (FL Games) and address each of the above challenges.  ... 
arXiv:2205.11101v1 fatcat:zpnp7mjsozaorecamjldunx6ii

Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation [article]

Kate Donahue, Jon Kleinberg
2020 arXiv   pre-print
If agents are drawing their data from different distributions, though, federated learning might produce a biased global model that is not optimal for each agent.  ...  Federated learning is a setting where agents, each with access to their own data source, combine models from local data to create a global model.  ...  We are grateful to A. F. Cooper, Thodoris Lykouris, Hakim Weathersppon, and the AI in Policy and Practice working group at Cornell for invaluable discussions. In particular, we thank A.F.  ... 
arXiv:2010.00753v3 fatcat:ygjxw5awgvc2baq6erqwsipt3i
« Previous Showing results 1 — 15 out of 20,110 results