检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tapo, Allahsera Auguste Traoré, Ali Danioko, Sidy Tembine, Hamidou Learning & Game Theory Laboratory TIMADIE

In the last 5 years, the availability of large audio datasets in African countries has opened unlimited opportunities to build machine intelligence (MI) technologies that are closer to the people and speak, learn, understand, and do businesses in local languages, including for those who cannot read and write. Unfortunately, these audio datasets are not fully exploited by current MI tools, leaving several Africans out of MI business opportunities. Additionally, many state-of-the-art MI models are not culture-aware, and the ethics of their adoption indexes are questionable. The lack thereof is a major drawback in many applications in Africa. This paper summarizes recent developments in machine intelligence in Africa from a multi-layer multiscale and culture-aware ethics perspective, showcasing MI use cases in 54 African countries through 400 articles on MI research, industry, government actions, as well as uses in art, music, the informal economy, and small businesses in Africa. The survey also opens discussions on the reliability of MI rankings and indexes in the African continent as well as algorithmic definitions of unclear terms used in MI. © 2024, CC BY.

关键词： game theory

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Mean-Field-Type games Driven by Five Noises 63

Multi-Layer Mean-Field-Type Games Driven by Five Noises

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Duncan, Tyrone E. Pasik-Duncan, Bozenna Tembine, Hamidou University of Kansas Department of Mathematics LawrenceKS66045 United States Learning and Game Theory Laboratory Timadie Paris75116 France University of Quebec at Trois-Rivieres Quebec Canada

ISBN: (纸本)9798350316339

Gaussian and Poisson noises have been widely studied in mean-field-type game theory. In this paper, we examine the effect of the noise in the equilibrium strategies. We show that the equilibrium strategies obtained under states driven by Brownian motions, Fractional Brownian motions, Gauss-Volterra and Poisson processes no longer provide equilibrium when mixed with Rosenblatt noises. The result suggests a careful understanding of the noise structures involved in the quantities of interests in the state dynamics before approximating it by standard Gaussian noises. © 2024 IEEE.

关键词： Brownian movement

来源：评论

学校读者我要写书评

暂无评论

Mean-Field-Type games driven by Rosenblatt Processes

Mean-Field-Type Games driven by Rosenblatt Processes

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Tyrone E. Duncan Bozenna Pasik-Duncan Hamidou Tembine Department of Mathematics University of Kansas Lawrence KS Learning and Game Theory Laboratory TIMADIE Paris

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

This paper examines a class of mean-field-type games with finite numbers of decision-makers with state dynamics driven by Rosenblatt processes. Rosen-blatt processes are non-Gaussian, non-Poisson, and non-Markov with long-range dependence. We provide equilibrium strategies and equilibrium costs in linear state-and-mean-field-type feedback form for all decision-makers. Interestingly, we show that the equilibrium strategies for state driven by Brownian, multi-fractional Brownian, Gauss-Volterra processes no longer provide equilibrium in presence of Rosenblatt processes.

关键词： Costs games Dynamic programming Information technology

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Mean-Field Type Control of Price Dynamics for Electricity in Smart Grid

引用

Journal of Systems Science & Complexity 2022年第1期35卷 1-17页

作者： FRIHI Zahrate El Oula CHOUTRI Salah Eddine BARREIRO-GOMEZ Julian TEMBINE Hamidou Laboratory of Probability and Statistics(La PS) Department of MathematicsBadji-Mokhtar UniversityB.P.12Annaba 23000Algeria. NYUAD Research Institute New York University Abu DhabiUAE Learning&Game Theory Laboratory New York University Abu DhabiSaadiyat Campus PO Box 129188UAE

This paper solves a mean-field type hierarchical optimal control problem in electricity *** authors consider n-1 prosumers and one *** ith prosumer,for 1<i<n,is a leader of the(i-1)th prosumer and is a follower ... 详细信息

This paper solves a mean-field type hierarchical optimal control problem in electricity *** authors consider n-1 prosumers and one *** ith prosumer,for 1

关键词： Electricity price dynamics hierarchical control mean-field-type control smart grids

来源：评论

学校读者我要写书评

暂无评论

The outcomes of generative AI are exactly the Nash equilibria of a non-potential game

arXiv

引用

arXiv 2024年

作者： Djehiche, Boualem Tembine, Hamidou Department of Mathematics KTH Royal Institute of Technology Stockholm10044 Sweden Learning and Game Theory Laboratory TIMADIE Paris75116 France

In this article we show that the asymptotic outcomes of both shallow and deep neural networks such as those used in BloombergGPT to generate economic time series are exactly the Nash equilibria of a non-potential game. We then design and analyze deep neural network algorithms that converge to these equilibria. The methodology is extended to federated deep neural networks between clusters of regional servers and on-device clients. Finally, the variational inequalities behind large language models including encoder-decoder related transformers are established. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Mean-Field-Type games Driven by Five Noises

Multi-Layer Mean-Field-Type Games Driven by Five Noises

引用

IEEE Conference on Decision and Control

作者： Tyrone E. Duncan Bozenna Pasik-Duncan Hamidou Tembine Department of Mathematics University of Kansas Lawrence KS Learning and Game Theory Laboratory TIMADIE Paris University of Quebec at Trois-Rivieres Quebec Canada

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

关键词： Brownian motion Gaussian noise Dynamics games game theory Standards

来源：评论

学校读者我要写书评

暂无评论

DEDPUL: Difference-of-Estimated-Densities-based Positive-Unlabeled learning 19

DEDPUL: Difference-of-Estimated-Densities-based Positive-Unl...

引用

19th IEEE International Conference on Machine learning and Applications, ICMLA 2020

作者： Ivanov, Dmitry Hse University International Laboratory of Game Theory and Decision Making Agent Systems and Reinforcement Learning Group JetBrains Research Saint-Petersburg Russia

ISBN: (纸本)9781728184708

Positive-Unlabeled (PU) learning is an analog to supervised binary classification for the case when only the positive sample is clean, while the negative sample is contaminated with latent instances of positive class and hence can be considered as an unlabeled mixture. The objectives are to classify the unlabeled sample and train an unbiased positive-negative classifier, which generally requires to identify the mixing proportions of positives and negatives first. Recently, unbiased risk estimation framework has achieved state-of-the-art performance in PU learning. This approach, however, exhibits two major bottlenecks. First, the mixing proportions are assumed to be identified, i.e. known in the domain or estimated with additional methods. Second, the approach relies on the classifier being a neural network. In this paper, we propose DEDPUL, a method that solves PU learning without the aforementioned issues. The mechanism behind DEDPUL is to apply a computationally cheap postprocessing procedure to the predictions of any classifier trained to distinguish positive and unlabeled data. Instead of assuming the proportions to be identified, DEDPUL estimates them alongside with classifying unlabeled sample. Experiments show that DEDPUL outperforms the current state-of-the-art in both proportion estimation and PU Classification and is flexible in the choice of the classifier. © 2020 IEEE.

关键词： Mixing

来源：评论

学校读者我要写书评

暂无评论

Distributed Planning in Mean-Field-Type games ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 2183-2188页

作者： Hamidou Tembine Learning & Game Theory Laboratory New York University Abu Dhabi Saadiyat Campus PO Box 129188 UAE Center on Stability Instability and Turbulence New York University Abu Dhabi Saadiyat Campus PO Box 129188 UAE

In this paper we study the problem of designing a collection of terminal payoff of mean-field type by interacting decision-makers to a specified terminal measure. We solve in a semi-explicit way a class of distributed planning in mean-field-type games with different objective functionals. We establish some relationships between the proposed framework, optimal transport theory, and distributed control of dynamical systems.

关键词： game theory optimal control stochastic control planning mean-field-type games

来源：评论

学校读者我要写书评

暂无评论

MatLab Toolbox for Linear-Quadratic Mean-Field-Type games: Version I

MatLab Toolbox for Linear-Quadratic Mean-Field-Type Games: V...

引用

IEEE Colombian Conference on Automatic Control (CCAC)

作者： Julian Barreiro-Gomez Hamidou Tembine Learning & Game Theory Laboratory New York University Abu Dhabi UAE

In this paper, a MatLab-based toolbox to simulate Linear-Quadratic Mean-Field-Type games (MFTGs) is presented. The toolbox consists of a first version that considers three different approaches for the one-dimensional case, i.e., Non-Cooperative, Fully-Cooperative and Co-opetitive MFTG scenarios are presented. In order to illustrate the use of the aforementioned tools, several examples are shown and the files corresponding to the developed functions are provided.

关键词： Matlab games Tools Differential equations Numerical models game theory Standards

来源：评论

学校读者我要写书评

暂无评论

Constrained Mean-Field-Type games: Stationary Case

Constrained Mean-Field-Type Games: Stationary Case

引用

IEEE Annual Conference on Decision and Control

作者： Julian Barreiro-Gomez Hamidou Tembine Learning & Game Theory Laboratory New York University Abu Dhabi United Arab Emirates

ISBN: (数字)9781728113982

ISBN: (纸本)9781728113999

In this paper, we study a class of constrained mean-field-type games with several decision-makers interacting in a stationary environment. The payoff functionals depend not only on the strategy profile but also on the first moment. This novel static game approach leads to risk-aware solution concepts. We introduce several solution concepts: mean-field-type best-response strategies, mean-field-type generalized Nash equilibria, mean-field-type variational equilibria. We provide a structure of payoffs with a decomposition that includes variance-aware cost. We discuss some learning algorithms to reach mean-field-type best Nash equilibria under constraints. The methodology is extended to include migration costs and migration incentives for each decision-maker and each choice component.

关键词： games Cost function Nash equilibrium Power system dynamics Minimization Standards Random variables

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：