CIF: Small: Distributed Statistical Inference with Compressed Data

CIF：小型：使用压缩数据进行分布式统计推断

• 批准号: 1717943
• 负责人: Lifeng Lai
• 金额: $ 45万
• 依托单位: University of California-Davis
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-07-15 至 2022-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1717943&HistoricalAwards=false
• 关键词: CIF; Small; Distributed; Statistical; Inference

Due to the rapid growth of size and scale of datasets and desire to harnessing parallel processing capabilities of multiple machines, distributed statistical inference and machine learning, in which available data are stored in multiple machines who are allowed to communicate with each other with limited communication budgets, have attracted significant research interests. There are two basic scenarios for the distributed setting: sample partition and feature partition. Although there have been many recent work on the design of inference algorithms for the sample partition scenario, there has been limited work on the feature partition scenario. The focus of this project is to characterize the fundamental limits and develop distributed statistical algorithms for the feature partition scenario from information theoretic perspective.Compared with the sample partition scenario, the feature partition scenario is significantly more challenging. This research addresses these challenges by focusing on two research thrusts. Thrust 1 focuses on designing interactive encoding schemes for inference. The main idea is that, by interacting with each other, the terminals can coordinate their compression so that the decision maker can obtain more information about the parameter while using the same communication resources, which will lead to a better inference performance. Thrust 2 designs function computing schemes for inference, in which the machines compute a function of observations without recovering them first and then perform inference from this function. The main motivation for this idea is that recovering observations or a compressed version of them is not necessary in the distributed inference setup, as the final goal of the distributed inference is to infer the value of the unknown parameter.

由于数据集大小和规模的快速增长，以及希望利用多台机器的并行处理能力，分布式统计推理和机器学习，其中可用数据存储在多台机器中，允许这些机器以有限的通信预算相互通信，引起了人们的广泛研究兴趣。分布式设置有两种基本场景：样本分区和特征分区。尽管最近在样本划分场景的推理算法设计方面已经有很多工作，但在特征划分场景方面的工作却很有限。该项目的重点是从信息论的角度表征特征划分场景的基本限制并开发分布式统计算法。与样本划分场景相比，特征划分场景明显更具挑战性。本研究通过关注两个研究重点来应对这些挑战。主旨 1 侧重于设计用于推理的交互式编码方案。其主要思想是，通过终端之间的交互，可以协调它们的压缩，使得决策者可以在使用相同的通信资源的同时获得更多的参数信息，从而获得更好的推理性能。 Thrust 2 设计了用于推理的函数计算方案，其中机器计算观测值的函数而不首先恢复它们，然后根据该函数执行推理。这个想法的主要动机是，在分布式推理设置中不需要恢复观测值或其压缩版本，因为分布式推理的最终目标是推断未知参数的值。

项目成果

ACTION-MANIPULATION ATTACKS ON STOCHASTIC BANDITS

对随机强盗的行动操纵攻击

• 发表时间: 2020-01
• 期刊: and Signal Processing
• 作者: Liu, Guanlin;Lai, Lifeng
• 通讯作者: Lai, Lifeng

Communication efficient distributed learning with feature partitioned data

使用特征分区数据进行高效通信的分布式学习

• DOI: 10.1109/ciss.2018.8362294
• 发表时间: 2018-05
• 期刊: 52nd Annual Conference on Information Sciences and Systems (CISS
• 作者: Zhang, Bingwen;Geng, Jun;Xu, Weiyu;Lai, Lifeng
• 通讯作者: Lai, Lifeng

Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense

针对随机强盗的动作操纵攻击：攻击与防御

• DOI: 10.1109/tsp.2020.3021525
• 发表时间: 2020-01
• 期刊: IEEE Transactions on Signal Processing
• 影响因子: 5.4
• 作者: Liu, Guanlin;Lai, Lifeng
• 通讯作者: Lai, Lifeng

Distributed Gradient Descent Algorithm Robust to an Arbitrary Number of Byzantine Attackers

对任意数量的拜占庭攻击者具有鲁棒性的分布式梯度下降算法

• DOI: 10.1109/tsp.2019.2946020
• 发表时间: 2019-11
• 期刊: IEEE Transactions on Signal Processing
• 影响因子: 5.4
• 作者: Cao, Xinyang;Lai, Lifeng
• 通讯作者: Lai, Lifeng

Quick Best Action Identification in Linear Bandit Problems

线性强盗问题中的快速最佳动作识别

• DOI: 10.1109/acssc.2018.8645353
• 发表时间: 2018-10
• 期刊: and Computers
• 作者: Geng, Jun;Lai, Lifeng
• 通讯作者: Lai, Lifeng