English
Related papers

Related papers: Sum-Rate-Distortion Function for Indirect Multiter…

200 papers

One of the main focuses in distributed learning is communication efficiency, since model aggregation at each round of training can consist of millions to billions of parameters. Several model compression methods, such as gradient…

Information Theory · Computer Science 2022-06-29 Naifu Zhang , Meixia Tao , Jia Wang , Fan Xu

A significant bottleneck in federated learning (FL) is the network communication cost of sending model updates from client devices to the central server. We present a comprehensive empirical study of the statistics of model updates in FL,…

Machine Learning · Computer Science 2022-05-23 Nicole Mitchell , Johannes Ballé , Zachary Charles , Jakub Konečný

We prove a new outer bound on the rate-distortion region for the multiterminal source-coding problem. This bound subsumes the best outer bound in the literature and improves upon it strictly in some cases. The improved bound enables us to…

Information Theory · Computer Science 2007-07-16 Aaron B. Wagner , Venkat Anantharam

We study a lossy source coding problem with secrecy constraints in which a remote information source should be transmitted to a single destination via multiple agents in the presence of a passive eavesdropper. The agents observe noisy…

Information Theory · Computer Science 2015-02-19 Farshad Naghibi , Somayeh Salimi , Mikael Skoglund

Optimal algorithm design for federated learning (FL) remains an open problem. This paper explores the full potential of FL in practical edge computing systems where workers may have different computation and communication capabilities, and…

Machine Learning · Computer Science 2021-11-29 Yangchen Li , Ying Cui , Vincent Lau

This paper studies a class of source coding problems that combines elements of the CEO problem with the multiple description problem. In this setting, noisy versions of one remote source are observed by two nodes with encoders (which is…

Information Theory · Computer Science 2010-01-07 Rajiv Soundararajan , Aaron B. Wagner , Sriram Vishwanath

The distributed remote source coding (so-called CEO) problem is studied in the case where the underlying source, not necessarily Gaussian, has finite differential entropy and the observation noise is Gaussian. The main result is a new lower…

Information Theory · Computer Science 2019-02-08 Krishnan Eswaran , Michael Gastpar

In this paper, we present iterative algorithms that numerically compute the rate-distortion regions of two problems: the two-encoder multiterminal source coding problem and the Chief Executive Officer (CEO) problem, both under logarithmic…

Information Theory · Computer Science 2017-08-25 Yigit Ugur , Inaki Estella Aguerri , Abdellatif Zaidi

A two-terminal interactive function computation problem with alternating messages is studied within the framework of distributed block source coding theory. For any finite number of messages, a single-letter characterization of the…

Information Theory · Computer Science 2012-08-06 Nan Ma , Prakash Ishwar

Recently, a considerable amount of works have been made to tackle the communication burden in federated learning (FL) (e.g., model quantization, data sparsification, and model compression). However, the existing methods, that boost the…

Information Theory · Computer Science 2022-06-15 Xuan-Tung Nguyen , Minh-Duong Nguyen , Quoc-Viet Pham , Vinh-Quang Do , Won-Joo Hwang

Federated Learning (FL) makes a large amount of edge computing devices (e.g., mobile phones) jointly learn a global model without data sharing. In FL, data are generated in a decentralized manner with high heterogeneity. This paper studies…

Machine Learning · Statistics 2021-12-20 Xiang Li , Jiadong Liang , Xiangyu Chang , Zhihua Zhang

We consider a many-to-one wireless architecture for federated learning at the network edge, where multiple edge devices collaboratively train a model using local data. The unreliable nature of wireless connectivity, together with…

Networking and Internet Architecture · Computer Science 2021-02-17 Junshan Zhang , Na Li , Mehmet Dedeoglu

Recently, federated learning (FL), which replaces data sharing with model sharing, has emerged as an efficient and privacy-friendly machine learning (ML) paradigm. One of the main challenges in FL is the huge communication cost for model…

Signal Processing · Electrical Eng. & Systems 2023-02-14 Huiyuan Yang , Tian Ding , Xiaojun Yuan

We study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, $K \geq 2$ agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian source, and…

Information Theory · Computer Science 2020-02-05 Yigit Ugur , Inaki Estella Aguerri , Abdellatif Zaidi

In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, $K \geq 2$ agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian…

Information Theory · Computer Science 2019-02-27 Yigit Ugur , Inaki Estella Aguerri , Abdellatif Zaidi

Edge computing allows artificial intelligence and machine learning models to be deployed on edge devices, where they can learn from local data and collaborate to form a global model. Federated learning (FL) is a distributed machine learning…

Machine Learning · Computer Science 2024-05-03 Chris Xing Tian , Yibing Liu , Haoliang Li , Ray C. C. Cheung , Shiqi Wang

An $n$-dimensional source with memory is observed by $K$ isolated encoders via parallel channels, who compress their observations to transmit to the decoder via noiseless rate-constrained links while leveraging their memory of the past. At…

Information Theory · Computer Science 2021-11-25 Victoria Kostina , Babak Hassibi

This paper studies a variant of the rate-distortion problem motivated by task-oriented semantic communication and distributed learning systems, where $M$ correlated sources are independently encoded for a central decoder. The decoder has…

Information Theory · Computer Science 2025-01-24 Jiancheng Tang , Qianqian Yang

This paper studies a variant of the rate-distortion problem motivated by task-oriented semantic communication and distributed learning problems, where $M$ correlated sources are independently encoded for a central decoder. The decoder has…

Information Theory · Computer Science 2024-05-24 Jiancheng Tang , Qianqian Yang , Deniz Gündüz

A fundamental issue for federated learning (FL) is how to achieve optimal model performance under highly dynamic communication environments. This issue can be alleviated by the fact that modern edge devices usually can connect to the edge…

Machine Learning · Computer Science 2021-09-21 Haizhou Du , Xiaojie Feng , Qiao Xiang , Haoyu Liu
‹ Prev 1 2 3 10 Next ›