CIF: Small: Collaborative Research: Inference by social sampling

CIF：小型：协作研究：社会抽样推断

• 批准号: 1440033
• 负责人: Anand Sarwate
• 金额: $ 17.58万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-01-01 至 2017-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1440033&HistoricalAwards=false
• 关键词: CIF; Small; Collaborative; Research; Inference

Learning and inference in distributed settings is an important from both a scientific and engineering perspective. A typical instance of the problem is a network of individual sensors or agents attempting to infer a global distribution that governs their local observations. By passing messages the agents can individually make inference about a global phenomenon. This research investigates communication and networking paradigms that can enable a network of individual agents to collaboratively estimate distributions over high dimensional spaces, even when individual observations are severely limited in accuracy, space, or time. In particular, the investigators study how individual decision makers can integrate two kinds of information: local observations and messages from their neighbors in the network. Both observation and messaging can be thought of as sampling : individuals sample their own environment and sample the opinions of their neighbors. Central to the approach is that the agents generate simple messages at random from an internal estimate of the global distribution of interest. The first major goal of this project is to develop a mathematical framework and analysis techniques to understand if and when this limited form of learning and communication is sufficient for an individual to estimate and learn distributions and/or global parameters governing the observations of all nodes. The technical approach is a blend of analysis techniques ranging from stochastic approximation, randomized algorithms, and statistical physics. Applications for this work range from mathematical modeling of messages and opinion formation in social networks, communication protocols for distributed optimization, and estimation of parameters in data networks. The work will cover several related problems : estimating high-dimensional histograms of data held in the network, parametric estimation using a mix of Bayesian and non-Bayesian techniques, and estimation of more complex generative models. The final part of the work is to apply these methods to peer-peer networks and social network modeling. The broader impact of this work is to further develop the interdisciplinary field of network science, which impacts both quantitative social sciences and engineering. The PIs will develop educational materials and organize research activities to help bring together different research communities interested in networks and social learning.

从科学和工程的角度来看，分布式环境中的学习和推理都很重要。 该问题的一个典型实例是单个传感器或代理的网络试图推断控制其局部观测的全局分布。 通过传递消息，代理可以单独推断全球现象。 这项研究调查了通信和网络范式，即使个体观察在准确性、空间或时间方面受到严重限制，这些范式也可以使个体代理网络能够协作估计高维空间上的分布。研究人员特别研究了个体决策者如何整合两种信息：本地观察和来自网络中邻居的消息。 观察和消息传递都可以被认为是采样：个体对自己的环境进行采样并采样邻居的意见。 该方法的核心是代理根据兴趣的全局分布的内部估计随机生成简单的消息。 该项目的第一个主要目标是开发一个数学框架和分析技术，以了解这种有限的学习和交流形式是否以及何时足以让个人估计和学习控制所有节点观测的分布和/或全局参数。 技术方法融合了随机近似、随机算法和统计物理学等分析技术。 这项工作的应用范围包括社交网络中消息和意见形成的数学建模、分布式优化的通信协议以及数据网络中的参数估计。 这项工作将涵盖几个相关问题：估计网络中数据的高维直方图、混合使用贝叶斯和非贝叶斯技术的参数估计以及更复杂的生成模型的估计。 工作的最后一部分是将这些方法应用于点对点网络和社交网络建模。 这项工作更广泛的影响是进一步发展网络科学的跨学科领域，这对定量社会科学和工程学都有影响。 PI 将开发教育材料并组织研究活动，以帮助汇集对网络和社交学习感兴趣的不同研究团体。

项目成果

Data Dependent Convergence For Consensus Stochastic Optimization

共识随机优化的数据依赖收敛

• DOI: 10.1109/tac.2017.2671377
• 发表时间: 2017-10
• 期刊: IEEE Transactions on Automatic Control
• 影响因子: 6.8
• 作者: Bijral, Avleen;Sarwate, Anand D.;Srebro, Nathan
• 通讯作者: Srebro, Nathan

Distributed Learning of Distributions via Social Sampling

通过社会抽样进行分布的分布式学习

• DOI: 10.1109/tac.2014.2329611
• 发表时间: 2013-05-20
• 期刊: IEEE Transactions on Automatic Control
• 影响因子: 6.8
• 作者: A. Sarwate;T. Javidi
• 通讯作者: T. Javidi

Data-dependent bounds on network gradient descent

网络梯度下降的数据相关界限

• DOI: 10.1109/allerton.2016.7852325
• 发表时间: 2016-09-01
• 期刊: 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
• 作者: A. Bijral;A. Sarwate;N. Srebro
• 通讯作者: N. Srebro

Social Learning and Distributed Hypothesis Testing

社会学习和分布式假设检验

• DOI: 10.1109/tit.2018.2837050
• 发表时间: 2018-09
• 期刊: IEEE Transactions on Information Theory
• 影响因子: 2.5
• 作者: Lalitha, Anusha;Javidi, Tara;Sarwate, Anand D.
• 通讯作者: Sarwate, Anand D.

Distributed proportional stochastic coordinate descent with social sampling

具有社会抽样的分布式比例随机坐标下降

• DOI: 10.1109/allerton.2015.7446981
• 发表时间: 2015-09
• 期刊: and Computing (Allerton
• 作者: Ghassemi, Mohsen;Sarwate, Anand D.
• 通讯作者: Sarwate, Anand D.