Zobrazeno 1 - 10
of 385
pro vyhledávání: '"68W15"'
Distributed learning algorithms, such as the ones employed in Federated Learning (FL), require communication compression to reduce the cost of client uploads. The compression methods used in practice are often biased, which require error feedback to
Externí odkaz:
http://arxiv.org/abs/2412.04538
In many modern computer application problems, the classification of image data plays an important role. Among many different supervised machine learning models, convolutional neural networks (CNNs) and linear discriminant analysis (LDA) as well as so
Externí odkaz:
http://arxiv.org/abs/2410.23359
In this paper, we propose a distributed first-order algorithm with backtracking linesearch for solving multi-agent minimisation problems, where each agent handles a local objective involving nonsmooth and smooth components. Unlike existing methods th
Externí odkaz:
http://arxiv.org/abs/2410.15583
Conventional tomographic reconstruction typically depends on centralized servers for both data storage and computation, leading to concerns about memory limitations and data privacy. Distributed reconstruction algorithms mitigate these issues by part
Externí odkaz:
http://arxiv.org/abs/2410.06106
Optimal transport on a graph focuses on finding the most efficient way to transfer resources from one distribution to another while considering the graph's structure. This paper introduces a new distributed algorithm that solves the optimal transport
Externí odkaz:
http://arxiv.org/abs/2410.05509
Autor:
Ortega, Tomas, Jafarkhani, Hamid
Recent advances in federated learning have shown that asynchronous variants can be faster and more scalable than their synchronous counterparts. However, their design does not include quantization, which is necessary in practice to deal with the comm
Externí odkaz:
http://arxiv.org/abs/2410.00242
Deep convolutional neural networks (CNNs) have been shown to be very successful in a wide range of image processing applications. However, due to their increasing number of model parameters and an increasing availability of large amounts of training
Externí odkaz:
http://arxiv.org/abs/2408.14442
Autor:
Tao, Luoyi
This study develops an algorithm for distributed computing of linear programming problems of huge-scales. Global consensus with single common variable, multiblocks, and augmented Lagrangian are adopted. The consensus is used to partition the constrai
Externí odkaz:
http://arxiv.org/abs/2408.06204
The segmentation of ultra-high resolution images poses challenges such as loss of spatial information or computational inefficiency. In this work, a novel approach that combines encoder-decoder architectures with domain decomposition strategies to ad
Externí odkaz:
http://arxiv.org/abs/2407.21266
Multi-dimensional Fourier transforms are key mathematical building blocks that appear in a wide range of applications from materials science, physics, chemistry and even machine learning. Over the past years, a multitude of software packages targetin
Externí odkaz:
http://arxiv.org/abs/2406.05577