arXiv subjects

Chung-Wei Weng

Publications and source records attributed to Chung-Wei Weng.

5 recordsLinked to original sources

arXiv2024

Differentially-Private Collaborative Online Personalized Mean Estimation

We consider the problem of collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. In particular, we provide a method based on hypothesis testing coupled with differential privacy and data variance estimation. Two privacy mechanisms and two data variance estimation schemes are proposed, and we provide a theoretical convergence analysis of the proposed algorithm for any bounded unknown distributions on the agents' data, showing that collaboration provides faster convergence than a fully local approach where agents do not share data. Moreover, we provide analytical performance curves for the case with an oracle class estimator, i.e., the class structure of the agents, where agents receiving data from distributions with the same mean are considered to be in the same class, is known. The theoretical faster-than-local convergence guarantee is backed up by extensive numerical results showing that for a considered scenario the proposed approach indeed converges much faster than a fully local approach, and performs comparably to ideal performance where all data is public. This illustrates the benefit of private collaboration in an online setting.

cs.LG↗

arXiv2024

Straggler-Resilient Differentially-Private Decentralized Learning

We consider the straggler problem in decentralized learning over a logical ring while preserving user data privacy. Especially, we extend the recently proposed framework of differential privacy (DP) amplification by decentralization by Cyffers and Bellet to include overall training latency--comprising both computation and communication latency. Analytical results on both the convergence speed and the DP level are derived for both a skipping scheme (which ignores the stragglers after a timeout) and a baseline scheme that waits for each node to finish before the training continues. A trade-off between overall training latency, accuracy, and privacy, parameterized by the timeout of the skipping scheme, is identified and empirically validated for logistic regression on a real-world dataset and for image classification using the MNIST and CIFAR-10 datasets.

cs.LG↗

arXiv2022

Generative Adversarial User Privacy in Lossy Single-Server Information Retrieval

We propose to extend the concept of private information retrieval by allowing for distortion in the retrieval process and relaxing the perfect privacy requirement at the same time. In particular, we study the trade-off between download rate, distortion, and user privacy leakage, and show that in the limit of large file sizes this trade-off can be captured via a novel information-theoretical formulation for datasets with a known distribution. Moreover, for scenarios where the statistics of the dataset is unknown, we propose a new deep learning framework by leveraging a generative adversarial network approach, which allows the user to learn efficient schemes from the data itself. We evaluate the performance of the scheme on a synthetic Gaussian dataset as well as on the MNIST, CIFAR-10, and LSUN datasets. For the MNIST, CIFAR-10, and LSUN datasets, the data-driven approach significantly outperforms a nonlearning-based scheme which combines source coding with the download of multiple files.

cs.LG↗

arXiv2018

SDN - Architectural Enabler for Reliable Communication over Millimeter-Wave 5G Networks

Millimeter-wave (mmWave) frequency bands offer a new frontier for next-generation wireless networks, popularly known as 5G, to enable multi-gigabit communication; however, the availability and reliability of mmWave signals are significantly limited due to its unfavorable propagation characteristics. Thus, mmWave networks rely on directional narrow-beam transmissions to overcome severe path-loss. To mitigate the impact of transmission-reception directionality and provide uninterrupted network services, ensuring the availability of mmWave transmission links is important. In this paper, we proposed a new flexible network architecture to provide efficient resource coordination among serving basestations during user mobility. The key idea of this holistic architecture is to exploit the software-defined networking (SDN) technology with mmWave communication to provide a flexible and resilient network architecture. Besides, this paper presents an efficient and seamless uncoordinated network operation to support reliable communication in highly-dynamic environments characterized by high density and mobility of wireless devices. To warrant high-reliability and guard against the potential radio link failure, we introduce a new transmission framework to ensure that there is at least one basestation is connected to the UE at all times. We validate the proposed transmission scheme through simulations.

cs.NI↗

arXiv2018

Enabling Millimeter-Wave 5G Networks for Massive IoT Applications

Internet of Things is one of the most promising technology of the fifth-generation (5G) mobile broadband systems. Data-driven wireless services of 5G systems require unprecedented capacity and availability. The millimeter-wave based wireless communication technologies are expected to play an essential role in future 5G systems. In this article, we describe the three broad categories of fifth-generation services, viz., enhanced mobile broadband, ultra-reliable and low-latency communications, and massive machine-type communications. Furthermore, we introduce the potential issues of consumer devices under a unifying 5G framework. We provide the state-of-the-art overview with an emphasis on technical challenges when applying millimeter-wave (mmWave) technology to support the massive Internet of Things applications. Our discussion highlights the challenges and solutions, particularly for communication/computation requirements in consumer devices under the millimeter-wave 5G framework.

cs.NI↗