Filters








9,516 Hits in 4.2 sec

Local Differential Privacy for Regret Minimization in Reinforcement Learning [article]

Evrard Garcelon, Vianney Perchet, Ciara Pike-Burke, Matteo Pirotta
<span title="2021-10-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Reinforcement learning algorithms are widely used in domains where it is desirable to provide a personalized service.  ...  We formulate this notion of privacy for RL by leveraging the local differential privacy (LDP) framework.  ...  Locally Differentially Private Posterior Sampling for Reinforcement Learning: We now discuss how to adapt PSRL to ensure it is locally differentially private.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.07778v3">arXiv:2010.07778v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/76bncyh47zgr3bvtu5qf52gxnm">fatcat:76bncyh47zgr3bvtu5qf52gxnm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211031142559/https://arxiv.org/pdf/2010.07778v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/68/e9/68e95f229714486bbefabdbf205c59281fa372aa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.07778v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Differentially Private Regret Minimization in Episodic Markov Decision Processes [article]

Sayak Ray Chowdhury, Xingyu Zhou
<span title="2021-12-20">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We study regret minimization in finite horizon tabular Markov decision processes (MDPs) under the constraints of differential privacy (DP).  ...  This is motivated by the widespread applications of reinforcement learning (RL) in real-world sequential decision making problems, where protecting users' sensitive and private information is becoming  ...  Local differentially private regret minimization in reinforcement learning. arXiv preprint arXiv:2010.07778, 2020. Cynthia Dwork. Differential privacy: A survey of results.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.10599v1">arXiv:2112.10599v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nuiwxweo7vcajhfbjeiilo5zle">fatcat:nuiwxweo7vcajhfbjeiilo5zle</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211231030234/https://arxiv.org/pdf/2112.10599v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/57/d0/57d006f1f2f82efa2099094fcc032eaff812225d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.10599v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Differentially Private Reinforcement Learning with Linear Function Approximation

Xingyu Zhou
<span title="2022-02-24">2022</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bkffycotbvf47idfrgeu4lgcdq" style="color: black;">Proceedings of the ACM on Measurement and Analysis of Computing Systems</a> </i> &nbsp;
Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized services, where users' sensitive and private information needs to be protected, we study regret minimization in  ...  a building block for general private reinforcement learning.  ...  in reinforcement learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3508028">doi:10.1145/3508028</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/v4u3idqfwvcd5megi3gdroalli">fatcat:v4u3idqfwvcd5megi3gdroalli</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220619041248/https://dl.acm.org/doi/pdf/10.1145/3508028" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a8/45/a845a2860e9c1bf1ff83cf046e15fb4cdf3633f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3508028"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes [article]

Chonghua Liao and Jiafan He and Quanquan Gu
<span title="2021-10-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data.  ...  To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL with linear function approximation and local differential privacy (LDP) guarantees.  ...  Introduction Reinforcement learning (RL) algorithms have been studied extensively in the past decade.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.10133v1">arXiv:2110.10133v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gvvkdlzxr5eylcawjdp5xrmgcy">fatcat:gvvkdlzxr5eylcawjdp5xrmgcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211022054308/https://arxiv.org/pdf/2110.10133v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ea/3f/ea3f4349aa1d2ebe1e217d62041f411083d32b60.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.10133v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Shuffle Private Linear Contextual Bandits [article]

Sayak Ray Chowdhury, Xingyu Zhou
<span title="2022-02-11">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, there remains a fundamental gap in the utility achieved by learning algorithms under these two privacy models, e.g., Õ(√(T)) regret in the central model as compared to Õ(T^3/4) regret in the local  ...  Finally, under the practical scenario of non-unique users, we show that the regret of our shuffle private algorithm scale as Õ(T^2/3), which matches that the central model could achieve in this case.  ...  Locally differentially private (contextual) bandits learning. In NeurIPS, 2020.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.05567v1">arXiv:2202.05567v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z5mnuy4jtvhubfitvvfccfpvke">fatcat:z5mnuy4jtvhubfitvvfccfpvke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220216064315/https://arxiv.org/pdf/2202.05567v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/90/d2/90d2b0038732d3cdb2a882b9f5aba6069f37d850.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.05567v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-Armed Bandits with Local Differential Privacy [article]

Wenbo Ren, Xingyu Zhou, Jia Liu, Ness B. Shroff
<span title="2020-07-06">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee.  ...  In stochastic bandit systems, the rewards may refer to the users' activities, which may involve private information and the users may not want the agent to know.  ...  In European Workshop on Reinforcement Learning (EWRL). [24] Tossou, A. C. and Dimitrakakis, C. (2016). Algorithms for differentially private multi-armed bandits.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03121v1">arXiv:2007.03121v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eehdco6p4ndpffatetx47o4nzi">fatcat:eehdco6p4ndpffatetx47o4nzi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710072502/https://arxiv.org/pdf/2007.03121v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03121v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multi-Objective Optimization of Differentiated Urban Ring Road Bus Lines and Fares Based on Travelers' Interactive Reinforcement Learning

Xueyan Li, Xin Zhu, Baoyu Li
<span title="2021-12-02">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nzoj5rayr5hutlurimhzyjlory" style="color: black;">Symmetry</a> </i> &nbsp;
In the lower level, evolutionary multi agent model of travelers' bounded rational reinforcement learning with social interaction is introduced.  ...  In the upper level, we propose a multi-objective bus lines and fares optimization model in which the operator's profit and travelers' utility are set as objective functions.  ...  In the new model we have proposed, travelers' reinforcement learning behavior and social interaction for higher utility based on regret theory is introduced.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym13122301">doi:10.3390/sym13122301</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yxiqmawdvzgvlhlla5f7ypew7i">fatcat:yxiqmawdvzgvlhlla5f7ypew7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220502182443/https://mdpi-res.com/d_attachment/symmetry/symmetry-13-02301/article_deploy/symmetry-13-02301.pdf?version=1638440814" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/db/8c/db8cb0deccd792a8f9316b809d9a11239e34fd19.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/sym13122301"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Actor-Critic Policy Optimization in Partially Observable Multiagent Environments [article]

Sriram Srinivasan, Marc Lanctot, Vinicius Zambaldi, Julien Perolat, Karl Tuyls, Remi Munos, Michael Bowling
<span title="2020-06-12">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show several candidate policy update rules and relate them to a foundation of regret minimization and multiagent learning techniques for the one-shot and tabular cases, leading to previously unknown  ...  Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.  ...  Game Theory, Regret Minimization, and Multiagent Reinforcement Learning In multiagent RL (MARL), n = |N | = |{1, 2, · · · , n}| agents interact within the same environment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.09026v5">arXiv:1810.09026v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ftp3mpq4xbfippxefqqc4h6rpy">fatcat:ftp3mpq4xbfippxefqqc4h6rpy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623115044/https://arxiv.org/pdf/1810.09026v5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/64/c5/64c56820640d4fedb92e5724224c1aaa70a0c06f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.09026v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Differentially Private Meta-Learning [article]

Jeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar
<span title="2020-02-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then propose a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex  ...  Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning.  ...  ACKNOWLEDGMENTS This work was supported in part by DARPA FA875017C0141, the National Science Foundation grants IIS1618714, IIS1705121, and IIS1838017, an Okawa Grant, a Google Faculty Award, an Amazon  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05830v2">arXiv:1909.05830v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e37kmf6fsrdutcn2w2p5qarvxu">fatcat:e37kmf6fsrdutcn2w2p5qarvxu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321155105/https://arxiv.org/pdf/1909.05830v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.05830v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Private Reinforcement Learning with PAC and Regret Guarantees [article]

Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu
<span title="2020-09-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, we present lower bounds on sample complexity and regret for reinforcement learning subject to JDP.  ...  We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.  ...  In this paper we contribute to the study of reinforcement learning from the lens of differential privacy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09052v1">arXiv:2009.09052v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/piv3gjndg5g5lfnmnfo5qsxfuq">fatcat:piv3gjndg5g5lfnmnfo5qsxfuq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200923001730/https://arxiv.org/pdf/2009.09052v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09052v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

OpenSpiel: A Framework for Reinforcement Learning in Games [article]

Marc Lanctot, Edward Lockhart, Jean-Baptiste Lespiau, Vinicius Zambaldi, Satyaki Upadhyay, Julien Pérolat, Sriram Srinivasan, Finbarr Timbers, Karl Tuyls, Shayegan Omidshafiei, Daniel Hennes, Dustin Morrill (+15 others)
<span title="2020-09-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.  ...  This document serves both as an overview of the code base and an introduction to the terminology, core concepts, and algorithms across the fields of reinforcement learning, computational game theory, and  ...  Counterfactual Regret Minimization Counterfactual regret (CFR) minimization is a policy iteration algorithm for computing approximate equilibra in two-player zero-sum games [87] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.09453v6">arXiv:1908.09453v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/whv37nw3tfaxhit3lv7av74aha">fatcat:whv37nw3tfaxhit3lv7av74aha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930022412/https://arxiv.org/pdf/1908.09453v6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.09453v6" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Byzantine-Robust Federated Linear Bandits [article]

Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian
<span title="2022-04-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, we make our algorithm differentially private via a tree-based mechanism.  ...  In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model.  ...  Auer [2002] introduced the first finite-time regret analysis of linear bandit under the name "linear reinforcement learning".  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.01155v1">arXiv:2204.01155v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/64deqod4xfcmnbj34jtybxvzpa">fatcat:64deqod4xfcmnbj34jtybxvzpa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220606022139/https://arxiv.org/pdf/2204.01155v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2d/b6/2db6edd25d47b2bef4673cd175ddc071ad9c8775.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.01155v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Information Aggregation for Constrained Online Control

Tongxin Li, Yue Chen, Bo Sun, Adam Wierman, Steven Low
<span title="2021-05-31">2021</span> <i title="ACM"> Abstract Proceedings of the 2021 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems </i> &nbsp;
information can be efficiently learned using reinforcement learning algorithms.  ...  The central controller's goal is to minimize the cumulative cost; however, the controller has access to neither the feasible set nor the dynamics directly, which are determined by a remote local controller  ...  In this section, we discuss the use of model-free reinforcement learning (RL) to generate an aggregator functions .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3410220.3461737">doi:10.1145/3410220.3461737</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/glkbujs76bavlhw45ixmfnd66i">fatcat:glkbujs76bavlhw45ixmfnd66i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715050232/https://authors.library.caltech.edu/109387/1/3460085.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/31/bb/31bbdedb016dfa8edc441382ea74e7ba94ed3a98.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3410220.3461737"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Game of GANs: Game-Theoretical Models for Generative Adversarial Networks [article]

Monireh Mohebbi Moghadam, Bahar Boroomand, Mohammad Jalali, Arman Zareian, Alireza DaeiJavad, Mohammad Hossein Manshaei, Marwan Krunz
<span title="2022-01-03">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then present taxonomy to classify state-of-the-art solutions into three main categories: modified game models, modified architectures, and modified learning methods.  ...  Despite the improvement accomplished in GANs in the last few years, several issues remain to be solved.  ...  As differentially private GAN models provides a promising direction for generating private synthetic data, Fan et al. in [44] survey the existing approaches presented for this purpose. C.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.06976v3">arXiv:2106.06976v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mecyjeopxnesjfj7bcoiim3p3a">fatcat:mecyjeopxnesjfj7bcoiim3p3a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210620202610/https://arxiv.org/pdf/2106.06976v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bc/a9/bca9279a4ea4ed51f274be24888a4e01ee6247f0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.06976v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Comprehensive Survey of Incentive Mechanism for Federated Learning [article]

Rongfei Zeng, Chao Zeng, Xingwei Wang, Bo Li, Xiaowen Chu
<span title="2021-06-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Subsequently, we summarize the existing incentive mechanisms in terms of the main techniques, such as Stackelberg game, auction, contract theory, Shapley value, reinforcement learning, blockchain.  ...  In such promising paradigm, the performance will be deteriorated without sufficient training data and other resources in the learning process.  ...  In sum, reinforcement learning can be innovatively applied for the incentive design in FL.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15406v1">arXiv:2106.15406v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7v7adaw5wnbldhykma6mhgpnty">fatcat:7v7adaw5wnbldhykma6mhgpnty</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210701103949/https://arxiv.org/pdf/2106.15406v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/46/fa/46fa2ef11417b75250945f98a538742de8ea99c4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15406v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 9,516 results