Related papers: Flare: Flexible In-Network Allreduce
According to the pay-per-use model adopted in clouds, the more the resources consumed by an application running in a cloud computing environment, the greater the amount of money the owner of the corresponding application will be charged.…
With the advent of software-defined networking, network configuration through programmable interfaces becomes practical, leading to various on-demand opportunities for network routing update in multi-tenant datacenters, where tenants have…
Modern power systems are now in continuous process of massive changes. Increased penetration of distributed generation, usage of energy storage and controllable demand require introduction of a new control paradigm that does not rely on…
Software-defined networks have been proposed as a viable solution to decrease the power consumption of the networking component in data center networks. Still the question remains on which scheduling algorithms are most suited to achieve…
We propose constant approximation algorithms for generalizations of the Flexible Flow Shop (FFS) problem which form a realistic model for non-preemptive scheduling in MapReduce systems. Our results concern the minimization of the total…
We study the compressive diffusion strategies over distributed networks based on the diffusion implementation and adaptive extraction of the information from the compressed diffusion data. We demonstrate that one can achieve a comparable…
As the scale of distributed training grows, communication becomes a bottleneck. To accelerate the communication, recent works introduce In-Network Aggregation (INA), which moves the gradients summation into network middle-boxes, e.g.,…
In the era of post-Moore computing, network offload emerges as a solution to two challenges: the imperative for low-latency communication and the push towards hardware specialisation. Various methods have been employed to offload protocol-…
Distributed machine learning workloads use data and tensor parallelism for training and inference, both of which rely on the AllReduce collective to synchronize gradients or activations. However, AllReduce algorithms are delayed by the…
Distributionally Robust Optimization (DRO), which aims to find an optimal decision that minimizes the worst case cost over the ambiguity set of probability distribution, has been widely applied in diverse applications, e.g., network…
We consider a wireless distributed computing system based on the MapReduce framework, which consists of three phases: \textit{Map}, \textit{Shuffle}, and \textit{Reduce}. The system consists of a set of distributed nodes assigned to compute…
This paper studies the computation-communication tradeoff in a heterogeneous MapReduce computing system where each distributed node is equipped with different computation capability. We first obtain an achievable communication load for any…
To address the evolving landscape of next-generation mobile networks, characterized by an increasing number of connected users, surging traffic demands, and the continuous emergence of new services, a novel communication paradigm is…
The demand for large-scale deep learning is increasing, and distributed training is the current mainstream solution. Ring AllReduce is widely used as a data parallel decentralized algorithm. However, in a heterogeneous environment, each…
One of the key advantages of Software-Defined Networks (SDN) is the opportunity to integrate traffic engineering modules able to optimize network configuration according to traffic. Ideally, network should be dynamically reconfigured as…
In distributed optimization, a large number of machines alternate between local computations and communication with a coordinating server. Communication, which can be slow and costly, is the main bottleneck in this setting. To reduce this…
The increasing number of flexible devices and distributed energy resources in power grids renders the coordination of transmission and distribution systems increasingly complex. In this paper, we discuss and compare two different approaches…
Diffusion adaptation is a powerful strategy for distributed estimation and learning over networks. Motivated by the concept of combining adaptive filters, this work proposes a combination framework that aggregates the operation of multiple…
In this paper, we consider a network of processors aiming at cooperatively solving mixed-integer convex programs subject to uncertainty. Each node only knows a common cost function and its local uncertain constraint set. We propose a…
Increasing penetration of Photovoltaic (PV) generation brings an opportunity, and sometimes necessity, for this new resource to provide ancillary services such as frequency support. Recent efforts toward this goal focused mainly on the…