权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

On intelligenCE And Networks - Synergistic research in Bayesian Statistics, Microeconomics and Computer Sciences - OCEAN

论智能与网络 - 贝叶斯统计、微观经济学和计算机科学的协同研究 - OCEAN

基本信息

批准号：
EP/Y014650/1
负责人：
Gareth Roberts
金额：
$ 240.05万
依托单位：
University of Warwick
依托单位国家：
英国
项目类别：
Research Grant
财政年份：
2023
资助国家：
英国
起止时间：
2023 至无数据
项目状态：
未结题

来源：
https://gtr.ukri.org/projects?ref=EP%2FY014650%2F1
关键词：
intelligenCE Networks Synergistic research Bayesian

项目摘要

Until recently, most of the major advances in machine learning and decision making have focused on a centralised paradigm in which data are aggregated at a central location to train models and/or decide on actions. This paradigm faces serious flaws in many real-world cases. In particular, centralised learning risks exposing user privacy, makes inefficient use of communication resources, creates data processing bottlenecks, and may lead to concentration of economic and political power. It thus appears most timely to develop the theory and practice of a new form of machine learning that targets heterogeneous, massively decentralised networks, involving self-interested agents who expect to receive value (or rewards, incentive) for their participation in data exchanges. OCEAN will develop statistical and algorithmic foundations for systems involving multiple incentive-driven learning and decision-making agents, including uncertainty quantification at the agent's level. OCEAN will study the interaction of learning with market constraints (scarcity, fairness), connecting adaptive microeconomics and market-aware machine learning. OCEAN builds on a decade of joint advances in stochastic optimisation, probabilistic machine learning, statistical inference, Bayesian assessment of uncertainty, computation, game theory, and information science, with PIs having complementary and internationally recognised skills in these domains. OCEAN will shed a new light on the value and handling data in a competitive, potentially antagonistic, multi-agent environment, and develop new theories and methods to address these pressing challenges. OCEAN will involve a fundamental departure from standard approaches and leads to major scientific interdisciplinary endeavours that will transform statistical learning in the long term while opening up exciting and novel areas of research.Crucial to our work will be the development of algorithms to achieve our aims. We will develop both optimisations and sampling tools, and our approach will be rigorous requiring theoretical results to underpin our methods. We will make contributions to the emerging field in Machine Learning called Federated Learning, and develop methodologies which have strong privacy and statistical guarantees. However while federated learning deals with distributed learning, we wish to go considerably further to consider interacting, decision-making networked agents (not just inert collectors of data). To achieve this we will need to introduce economic endgame-theoretic ideas to understand concepts such as competition and social welfare. We will develop multi-armed bandit methods to deal with strategic experimentation and also consider online matching procedures within a dynamic exchange network.The science behind OCEAN is a blend of new methods from numerical probability, Bayesian computational statistics, machine learning, distributed algorithms, multi-agent systems, and game theory, all deeply rooted in theoretical validation. Our vision to advance theory is critical to our proposal, as quantitative and rigorous statements about performance are essential to formulate meaningful trade-offs between computational, economic, and inferential goals.

直到最近，机器学习和决策方面的大多数主要进展都集中在一个集中的范例上，在这个范例中，数据被聚集在一个中央位置，以训练模型和/或决定行动。这一范式在许多现实世界的案例中面临严重缺陷。特别是，集中式学习有暴露用户隐私的风险，使通信资源使用效率低下，造成数据处理瓶颈，并可能导致经济和政治权力集中。因此，现在发展一种新的机器学习形式的理论和实践似乎是最及时的，这种机器学习的目标是异质的、大规模分散的网络，让自利的代理人参与到数据交换中，期望从他们的参与中获得价值(或奖励和激励)。海洋将为涉及多个激励驱动的学习和决策代理的系统开发统计和算法基础，包括代理级别的不确定性量化。Ocean将研究学习与市场约束(稀缺性、公平性)的相互作用，将适应性微观经济学和市场感知的机器学习联系起来。海洋建立在随机优化、概率机器学习、统计推理、不确定性的贝叶斯评估、计算、博弈论和信息科学十年共同进步的基础上，而私人投资机构在这些领域拥有互补的和国际公认的技能。海洋将对在竞争、潜在对立的多主体环境中的价值和处理数据提供新的认识，并开发新的理论和方法来应对这些紧迫的挑战。海洋将从根本上偏离标准方法，并导致重大的科学跨学科努力，从长远来看，这将改变统计学习，同时开辟令人兴奋的和新的研究领域。我们工作的关键将是开发算法，以实现我们的目标。我们将开发优化和抽样工具，我们的方法将是严格的，需要理论结果来支撑我们的方法。我们将为机器学习中的新兴领域联邦学习做出贡献，并开发具有强大隐私和统计保证的方法。然而，虽然联合学习涉及分布式学习，但我们希望更进一步地考虑交互、决策的联网代理(而不仅仅是惰性的数据收集者)。要实现这一点，我们将需要引入经济学终局理论，以理解竞争和社会福利等概念。我们将开发多臂强盗方法来处理战略实验，并考虑动态交换网络中的在线匹配程序。海洋背后的科学是数值概率、贝叶斯计算统计、机器学习、分布式算法、多代理系统和博弈论的新方法的混合，所有这些都深深植根于理论验证。我们推进理论的愿景对我们的提议至关重要，因为关于绩效的定量和严格的陈述对于在计算、经济和推理目标之间制定有意义的权衡至关重要。