Adaptive Networks

By Ali H. Sayed. Proceedings of the IEEE, 2014

735 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/f2cfab80035135f2c6dc0da6596a15fc96f0bd95

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Networks and Communications

Citations in the corpus

Distributed Policy Evaluation Under Multiple Behavior Strategies (2013, methodology): “Motivated by recent results on network behavior in [21], [45], we note that, through collaboration, each agent may contribute to the network with its own experience.”
Distributed learning for Random Vector Functional-Link networks (2015, background): “So far, a large body of research has gone into developing fully distributed, decentralized learning algorithms, including works on diffusion adaptation [21,34], learning by consensus [16], distributed learning on commodity clusters architectures [8], adaptation on WSNs [5,32], distributed online lea”
Exact Diffusion for Distributed Optimization and Learning—Part I: Algorithm Development (2017, background): “To solve problem (4) over a connected network of agents, we consider the standard diffusion strategy [13]–[15]:”
Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates (2018, methodology): “Some notable works in this area include [22]–[32].”
Robust Distributed Diffusion Recursive Least Squares Algorithms With Side Information for Adaptive Networks (2018, methodology): “is defined as MSDnet(i) = 1 N ∑N k=1 MSDk (i) = Tr{W i}/N [2].”
Adaptation, Learning, and Optimization over Networks (2014, methodology): “It provides an extended treatment of topics presented in condensed form in the survey [208], and of several other additional topics.”
A Framework for Parallel and Distributed Training of Neural Networks (2016, methodology): “Additional extensions can consider the presence of non-differentiable points in the NN model (e.g., by using ReLu activation functions), stochastic updates of the surrogate functions, and online formulations where new data arrives in a streaming fashion, like in distributed filtering (Sayed, 2014).”
Diff-DAC: Distributed Actor-Critic for Average Multitask Deep Reinforcement Learning (2017, methodology): “One of such procedures is the Hastings rule (Zhao and Sayed 2012), (Sayed 2014, p.492).”
Distributed Ridge Regression with Feature Partitioning (2018, methodology): “The algorithm in [6] is fully distributed and based on the diffusion strategy [26].”
Decentralized consensus optimization with asynchrony and delays (2016, background): “Like all other distributed gradient descent algorithms [6], [11]– [13], [36], however, algorithm (21) and its asynchronous version (22) must use diminishing step sizes to guarantee exact convergence, which causes slow convergence.”
Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization (2018, methodology): “This approach includes well-known algorithms such as diffusion [1], [2] and consensus [7], [8], distributed ADMM (D-ADMM) [9]–[13], EXTRA [14], PG-EXTRA [15], DIGing [16], exact diffusion [17], NIDS [18], and beyond.”
On the influence of momentum acceleration on online learning (2016, methodology): “It is nowadays well-recognized that the small O(µ) degradation in performance is acceptable in most large-scale learning and adaptation problems (Bousquet and Bottou, 2008; Bottou, 2010; Sayed, 2014b).”
Multitask Diffusion Adaptation Over Networks (2013, background): “Accessible overviews of recent results in the ﬁeld can be found in [1], [2].”
Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up (2019, background): “For a discussion on the difference between the two protocols we refer to [40].”