English
Related papers

Related papers: The Gradient Mechanism in a Communication Network

200 papers

Gradient descent (GD) methods are commonly employed in machine learning problems to optimize the parameters of the model in an iterative fashion. For problems with massive datasets, computations are distributed to many parallel computing…

Information Theory · Computer Science 2019-03-06 Emre Ozfatura , Deniz Gunduz , Sennur Ulukus

We study an information design problem in transportation networks, in the presence of a random state that affects the travel times on the links. An omniscient system planner -- aiming at reducing congestion -- observes the network state…

Optimization and Control · Mathematics 2025-09-04 Alexia Ambrogio , Leonardo Cianfanelli , Giacomo Como

This paper addresses a distributed optimization problem in a communication network where nodes are active sporadically. Each active node applies some learning method to control its action to maximize the global utility function, which is…

Optimization and Control · Mathematics 2021-04-20 Wenjie Li , Mohamad Assaad , Shiqi Zheng

We investigate the generalisation performance of Distributed Gradient Descent with Implicit Regularisation and Random Features in the homogenous setting where a network of agents are given data sampled independently from the same unknown…

Machine Learning · Statistics 2020-07-02 Dominic Richards , Patrick Rebeschini , Lorenzo Rosasco

The ability to achieve coordinated behavior --engineered or emergent-- on networked systems has attracted widespread interest over several fields. This has led to remarkable advances on the development of a theoretical understanding of the…

Systems and Control · Computer Science 2019-09-16 Hancheng Min , Enrique Mallada

We have studied experimentally transport properties in a slowly driven granular system which recently was shown to display self-organized criticality [Frette {\em et al., Nature} {\bf 379}, 49 (1996)]. Tracer particles were added to a pile…

Condensed Matter · Physics 2016-08-15 Kim Christensen , Álvaro Corral , Vidar Frette , Jens Feder , Torstein Jøssang

Decentralized Stochastic Gradient Descent (SGD) is an emerging neural network training approach that enables multiple agents to train a model collaboratively and simultaneously. Rather than using a central parameter server to collect…

Machine Learning · Computer Science 2023-06-02 Lisang Ding , Kexin Jin , Bicheng Ying , Kun Yuan , Wotao Yin

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

We study the transport efficiency of excitations on complex quantum networks with loops. For this we consider sequentially growing networks with different topologies of the sequential subgraphs. This can lead either to a universal complete…

Physics and Society · Physics 2016-02-24 Oliver Muelken , Maxim Dolgushev , Mircea Galiceanu

The goal of traffic management is efficiently utilizing network resources via adapting of source sending rates and routes selection. Traditionally, this problem is formulated into a utilization maximization problem. The single-path routing…

Networking and Internet Architecture · Computer Science 2015-03-19 Ying Liu , Hongying Liu , Ke Xu , Meng Shen , Yifeng Zhong

We study diffusion of information packets on several classes of structured networks. Packets diffuse from a randomly chosen node to a specified destination in the network. As local transport rules we consider random diffusion and an…

Statistical Mechanics · Physics 2015-06-24 Bosiljka Tadic , Stefan Thurner

Regional energy caps limit the growth of any single data center used for large-scale model training. This single-center training paradigm works when model size remains manageable, but exponential growth in the model size and computational…

Machine Learning · Computer Science 2025-12-18 Rongwei Lu , Jingyan Jiang , Chunyang Li , Xingguang Wei , Zhi Wang

The caching paradigm has been introduced to alleviate backhaul traffic load and to reduce latencies due to massive never ending increase in data traffic. To fully exploit the benefits offered by caching, unmanned aerial vehicles (UAVs) and…

Information Theory · Computer Science 2024-01-18 Emre Gures , Pavel Mach

We consider a dense, ad hoc wireless network, confined to a small region. The wireless network is operated as a single cell, i.e., only one successful transmission is supported at a time. Data packets are sent between sourcedestination…

Networking and Internet Architecture · Computer Science 2009-07-22 Venkatesh Ramaiyan , Anurag Kumar , Eitan Altman

Coherent transport promises to be the basis for an emerging new technology. Notwithstanding, a mechanistic understanding of the fundamental principles behind optimal scattering media is still missing. Here, complex network analysis is…

Quantum Physics · Physics 2013-12-09 Stefano Mostarda , Federico Levi , Diego Prada-Gracia , Florian Mintert , Francesco Rao

Data transfer in opportunistic Delay Tolerant Networks (DTNs) must rely on unscheduled sporadic meetings between nodes. The main challenge in these networks is to develop a mechanism based on which nodes can learn to make nearly optimal…

Networking and Internet Architecture · Computer Science 2015-06-19 Shohreh Shaghaghian , Mark Coates

Global transport and communication networks enable information, ideas and infectious diseases now to spread at speeds far beyond what has historically been possible. To effectively monitor, design, or intervene in such epidemic-like…

Physics and Society · Physics 2020-02-13 Sam Moore , Tim Rogers

This paper considers Gaussian relay networks where a source transmits a message to a sink terminal with the help of one or more relay nodes. The relays work in half-duplex mode, in the sense that they can not transmit and receive at the…

Information Theory · Computer Science 2018-10-16 Martina Cardone , Daniela Tuninetti , Raymond Knopp , Umer Salim

We study a distributed consensus-based stochastic gradient descent (SGD) algorithm and show that the rate of convergence involves the spectral properties of two matrices: the standard spectral gap of a weight matrix from the network…

Optimization and Control · Mathematics 2016-09-02 Avleen S. Bijral , Anand D. Sarwate , Nathan Srebro

By introducing a simple model based on two-dimensional cellular automata, we reveal the relationship between the routing strategies of individual vehicles and the global behavior of transportation networks. Specifically, we characterize the…

Physics and Society · Physics 2019-07-31 Tak Shing Tai , Chi Ho Yeung