Zobrazeno 1 - 10
of 1 928
pro vyhledávání: '"Ramakrishnan,K."'
Federated Learning (FL) typically involves a large-scale, distributed system with individual user devices/servers training models locally and then aggregating their model updates on a trusted central server. Existing systems for FL often use an alway
Externí odkaz:
http://arxiv.org/abs/2405.10968
A conjugate skew gain graph is a skew gain graph with the labels (also called, the conjugate skew gains) from the field of complex numbes on the oriented edges such that they get conjugated when we reverse the orientation. In this paper we introduce
Externí odkaz:
http://arxiv.org/abs/2307.05718
Hardware accelerators such as GPUs are required for real-time, low-latency inference with Deep Neural Networks (DNN). However, due to the inherent limits to the parallelism they can exploit, DNNs often under-utilize the capacity of today's high-end a
Externí odkaz:
http://arxiv.org/abs/2304.13541
Traditional network resident functions (e.g., firewalls, network address translation) and middleboxes (caches, load balancers) have moved from purpose-built appliances to software-based components. However, L2/L3 network functions (NFs) are being imp
Externí odkaz:
http://arxiv.org/abs/2303.04404
Publikováno v:
In Partial Differential Equations in Applied Mathematics December 2024 12
Autor:
K, Shahul Hameed, P, Remna K, T2, Divya, K, Biju, P, Rajeevan, O2, Santhosh G, O, Ramakrishnan K
A signed graph $\Sigma$ is a pair $(G,\sigma)$, where $G=(V,E)$ is the underlying graph in which each edge is assigned $+1$ or $-1$ by the signature function $\sigma:E\rightarrow\{-1,+1\}$. In this paper, we extend the extensively applied concepts of
Externí odkaz:
http://arxiv.org/abs/2106.12539
Serverless computing is increasingly popular because of its lower cost and easier deployment. Several cloud service providers (CSPs) offer serverless computing on their public clouds, but it may bring the vendor lock-in risk. To avoid this limitation
Externí odkaz:
http://arxiv.org/abs/2106.03601
Publikováno v:
IEEE/ACM Transactions on Networking, early access 2021
An appealing feature of Network Function Virtualization (NFV) is that in an NFV-based network, a network function (NF) instance may be placed at any node. On the one hand this offers great flexibility in allocation of redundant instances, but on the
Externí odkaz:
http://arxiv.org/abs/2008.13453
GPUs are used for training, inference, and tuning the machine learning models. However, Deep Neural Network (DNN) vary widely in their ability to exploit the full power of high-performance GPUs. Spatial sharing of GPU enables multiplexing several DNN
Externí odkaz:
http://arxiv.org/abs/2008.03602
Publikováno v:
Proceedings of the 5th International Workshop on Serverless Computing, Pages 37-42, 2019
Serverless computing is increasingly popular because of the promise of lower cost and the convenience it provides to users who do not need to focus on server management. This has resulted in the availability of a number of proprietary and open-source
Externí odkaz:
http://arxiv.org/abs/1911.07449