RINGS: REALTIME: Resilient Edge-cloud Autonomous Learning with Timely Inferences

RINGS：实时：具有及时推理能力的弹性边缘云自主学习

• 批准号: 2148104
• 负责人: Anand Sarwate
• 金额: $ 100万
• 依托单位: Rutgers University New Brunswick
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2148104&HistoricalAwards=false
• 关键词: RINGS; REALTIME; Resilient; Edge; cloud

Machine learning (ML) is the enabler of emerging real-time applications ranging from augmented reality and smart cities to autonomous vehicles that are changing how people live and work. Low latency is essential for these services; emerging real-time applications will typically need assistance from a mobile edge cloud (MEC) for real-time operation. This emerging scenario introduces significant new challenges: mobile devices are heterogeneous, ranging from energy-harvesting sensors to automobiles, but storage and compute resources are generally limited and communication is often over low-bandwidth channels; real-time deployment of trained ML models requires autonomous computation and decision-making that is adaptive to heterogeneous time-varying local environments; devices need to make high-accuracy inferences on high-dimensional data in real time; devices continuously gather new data that must be processed, aggregated, and communicated to the MEC; mobile users have heterogenous privacy preferences that require privacy-sensitive use of the MEC; and the applications and services on the mobile devices must be resilient to changes in both the cyber and physical worlds in order to ensure personal safety. This project is aimed at the design and experimental validation of an MEC-based distributed ML system that accounts for these factors.In this setting of real-time operation, online decision-making, and offline training of ML-based applications that must be resilient to data, application, user, and system changes, this research program has four facets: (1) Edge-centric distributed ML models to enable both real-time inferences at mobile devices and fast distributed semi-supervised training are being developed and evaluated. (2) Based on age-of-information timeliness metrics, real-time inference methods and system operation are optimized to balance mobile computation against network resources. (3) Differential privacy and other privacy metrics for real-time and online operation of MEC-assisted ML are being developed and incorporated in the distributed algorithms for system adaptation. (4) The project integrates these design approaches in a proof-of-concept prototype on the NSF COSMOS testbed in NY City to validate feasibility and evaluate device and system resilience for representative applications.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

机器学习 (ML) 是新兴实时应用的推动者，从增强现实和智能城市到自动驾驶汽车，这些应用正在改变人们的生活和工作方式。 低延迟对于这些服务至关重要；新兴的实时应用程序通常需要移动边缘云 (MEC) 的帮助才能实现实时操作。这种新兴场景带来了重大的新挑战：移动设备是异构的，从能量收集传感器到汽车，但存储和计算资源通常有限，并且通常通过低带宽信道进行通信； 实时部署经过训练的机器学习模型需要自主计算和决策，以适应异构时变本地环境；设备需要实时对高维数据进行高精度推断；设备不断收集必须处理、聚合并传送给 MEC 的新数据；移动用户具有异构的隐私偏好，需要对 MEC 进行隐私敏感的使用；移动设备上的应用程序和服务必须能够适应网络和物理世界的变化，以确保人身安全。 该项目旨在设计和实验验证基于 MEC 的分布式 ML 系统，该系统考虑了这些因素。在这种基于 ML 的应用程序的实时操作、在线决策和离线训练的设置中，必须具有弹性针对数据、应用程序、用户和系统的变化，该研究计划有四个方面：（1）正在开发和评估以边缘为中心的分布式机器学习模型，以实现移动设备上的实时推理和快速分布式半监督训练。 （2）基于信息时代的及时性指标，优化实时推理方法和系统操作，以平衡移动计算与网络资源。 (3) 正在开发用于 MEC 辅助机器学习实时在线操作的差分隐私和其他隐私指标，并将其纳入分布式算法中以进行系统适配。 (4) 该项目将这些设计方法集成到纽约市 NSF COSMOS 测试台上的概念验证原型中，以验证可行性并评估代表性应用的设备和系统弹性。该奖项反映了 NSF 的法定使命，并被认为是值得的通过使用基金会的智力优势和更广泛的影响审查标准进行评估来提供支持。

项目成果

FAST-PCA: A Fast and Exact Algorithm for Distributed Principal Component Analysis

FAST-PCA：一种快速准确的分布式主成分分析算法

• DOI: 10.1109/tsp.2022.3229635
• 发表时间: 2022-01
• 期刊: IEEE Transactions on Signal Processing
• 影响因子: 5.4
• 作者: Gang, Arpita;Bajwa, Waheed U.
• 通讯作者: Bajwa, Waheed U.

C-DIEGO: An Algorithm with Near-Optimal Sample Complexity for Distributed, Streaming PCA

C-DIEGO：一种具有近乎最优样本复杂度的分布式流式 PCA 算法

• DOI: 10.1109/ciss56502.2023.10089668
• 发表时间: 2023-03
• 期刊: 2023 57th Annual Conference on Information Sciences and Systems (CISS
• 作者: Zulqarnain, Muhammad;Gang, Arpita;Bajwa, Waheed U.
• 通讯作者: Bajwa, Waheed U.

Exit Time Analysis for Approximations of Gradient Descent Trajectories Around Saddle Points

鞍点周围梯度下降轨迹近似的退出时间分析

• DOI: 10.1093/imaiai/iaac025
• 发表时间: 2023-02
• 期刊: Information and Inference: A Journal of the IMA
• 作者: Dixit, Rishabh;Gürbüzbalaban, Mert;Bajwa, Waheed U
• 通讯作者: Bajwa, Waheed U

Privacy Leakage in Discrete-Time Updating Systems

离散时间更新系统中的隐私泄露

• DOI: 10.1109/isit50566.2022.9834673
• 发表时间: 2022-06
• 期刊: 2022 IEEE International Symposium on Information Theory (ISIT
• 作者: Sathyavageeswaran, Nitya;Yates, Roy D.;Sarwate, Anand D.;Mandayam, Narayan
• 通讯作者: Mandayam, Narayan

Distributed stochastic algorithms for high-rate streaming principal component analysis

用于高速流主成分分析的分布式随机算法

• 发表时间: 2022-10
• 期刊: Transactions on machine learning research
• 作者: Raja, Haroon;Bajwa, Waheed U.
• 通讯作者: Bajwa, Waheed U.