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

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式上，在这个范式中，数据聚集在一个中心位置，以训练模型和/或决定行动。这种范式在许多现实世界的案例中面临着严重的缺陷。特别是，集中式学习有暴露用户隐私的风险，使通信资源的利用效率低下，造成数据处理瓶颈，并可能导致经济和政治权力的集中。因此，发展一种新型机器学习的理论和实践似乎是最及时的，这种机器学习的目标是异构的、大规模去中心化的网络，涉及那些希望从参与数据交换中获得价值（或奖励、激励）的自利主体。OCEAN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，包括代理层面的不确定性量化。OCEAN将研究学习与市场约束（稀缺性、公平性）的相互作用，将自适应微观经济学与市场感知机器学习联系起来。OCEAN建立在十年来在随机优化、概率机器学习、统计推断、贝叶斯不确定性评估、计算、博弈论和信息科学方面的共同进步的基础上，pi在这些领域具有互补和国际公认的技能。OCEAN将为在竞争、潜在对抗、多代理环境下的价值和数据处理提供新的视角，并开发新的理论和方法来应对这些紧迫的挑战。OCEAN将涉及从根本上背离标准方法，并导致重大的科学跨学科努力，这将在长期内改变统计学习，同时开辟令人兴奋和新颖的研究领域。对我们的工作至关重要的是开发算法来实现我们的目标。我们将开发优化和抽样工具，我们的方法将是严格的，需要理论结果来支持我们的方法。我们将为机器学习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，当联邦学习处理分布式学习时，我们希望进一步考虑交互、决策的网络代理（而不仅仅是惰性的数据收集器）。要做到这一点，我们需要引入经济终局论思想，以理解竞争和社会福利等概念。我们将开发多武装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。OCEAN背后的科学融合了数值概率、贝叶斯计算统计、机器学习、分布式算法、多智能体系统和博弈论等新方法，这些方法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，因为关于性能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。

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.