SGD-Based Adaptive NN Control Design for Uncertain Nonlinear Systems

Yang, Xuebo; Zheng, Xiaolong; Gao, Huijun

doi:10.1109/tnnls.2018.2790479

Cited by 38 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to address the above problem, the first group of studies is directed towards different SGD modifications such as SGD with adopting extended differentiators [61], random reshuffling [62], local changes in gradients [63], [64] and etc.…”

Section: A Adaptive Optimizationmentioning

confidence: 99%

Step size self-adaptation for SGD

Kulikovskikh¹,

Legović²

2021

Preprint

View full text Add to dashboard Cite

<p>Convergence and generalization are two crucial aspects of performance in neural networks. When analyzed separately, these properties may lead to contradictory results. Optimizing a convergence rate yields fast training, but does not guarantee the best generalization error. To avoid the conflict, recent studies suggest adopting a moderately large step size for optimizers, but the added value on the performance remains unclear. We propose the LIGHT function with the four configurations which regulate explicitly an improvement in convergence and generalization on testing. This contribution allows to: 1) improve both convergence and generalization of neural networks with no need to guarantee their stability; 2) build more reliable and explainable network architectures with no need for overparameterization. We refer to it as step size self-adaptation.</p>

show abstract

Section: A Adaptive Optimizationmentioning

confidence: 99%

Step size self-adaptation for SGD

Kulikovskikh¹,

Legović²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to address the above problem, the first group of studies is directed towards different SGD modifications such as SGD with adopting extended differentiators [62], random reshuffling [63], local changes in gradients [64], [65] and etc.…”

Section: A Adaptive Optimizationmentioning

confidence: 99%

Painless step size adaptation for SGD

Kulikovskikh,

Legović

2021

Preprint

View full text Add to dashboard Cite

Convergence and generalization are two crucial aspects of performance in neural networks. When analyzed separately, these properties may lead to contradictory results. Optimizing a convergence rate yields fast training, but does not guarantee the best generalization error. To avoid the conflict, recent studies suggest adopting a moderately large step size for optimizers, but the added value on the performance remains unclear. We propose the LIGHT function with the four configurations which regulate explicitly an improvement in convergence and generalization on testing. This contribution allows to: 1) improve both convergence and generalization of neural networks with no need to guarantee their stability; 2) build more reliable and explainable network architectures with no need for overparameterization. We refer to it as "painless" step size adaptation.

show abstract

“…Besides, discrete variables in vector {I, B, H} are relaxed to continuous variables. Variables i m , b m , and h g are updated according to the SGD method in [41] to minimize the loss function.…”

Section: Function Approximation Based Algorithm For Large-scale Networkmentioning

confidence: 99%

Caching Placement and Resource Allocation for Cache-Enabling UAV NOMA Networks

Zhang

Wang

Liu

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

This article investigates the cache-enabling unmanned aerial vehicle (UAV) cellular networks with massive access capability supported by non-orthogonal multiple access (NOMA). The delivery of a large volume of multimedia contents for ground users is assisted by a mobile UAV base station, which caches some popular contents for wireless backhaul link traffic offloading. In cache-enabling UAV NOMA networks, the caching placement of content caching phase and radio resource allocation of content delivery phase are crucial for network performance. To cope with the dynamic UAV locations and content requests in practical scenarios, we formulate the longterm caching placement and resource allocation optimization problem for content delivery delay minimization as a Markov decision process (MDP). The UAV acts as an agent to take actions for caching placement and resource allocation, which includes the user scheduling of content requests and the power allocation of NOMA users. In order to tackle the MDP, we propose a Q-learning based caching placement and resource allocation algorithm, where the UAV learns and selects action with soft εgreedy strategy to search for the optimal match between actions and states. Since the action-state table size of Q-learning grows with the number of states in the dynamic networks, we propose a function approximation based algorithm with combination of stochastic gradient descent and deep neural networks, which is suitable for large-scale networks. Finally, the numerical results show that the proposed algorithms provide considerable performance compared to benchmark algorithms, and obtain a tradeoff between network performance and calculation complexity.Index termsdynamic resource allocation, non-orthogonal multiple access, reinforcement learning, unmanned aerial vehicle I. INTRODUCTIONWith the explosion of massive multimedia applications and the continuous growth of mobile data traffic, wireless communication faces the problem of limited resources. In order to effectively meet the increasing user demand for high data rate and low access delay, many works [1-5] have paid attention to wireless connectivity from the sky with unmanned aerial vehicles (UAVs). UAVs, also known as remotely piloted aircraft systems (RPAS) or drones, are small pilotless aircrafts

show abstract

SGD-Based Adaptive NN Control Design for Uncertain Nonlinear Systems

Cited by 38 publications

References 27 publications

Step size self-adaptation for SGD

Step size self-adaptation for SGD

Painless step size adaptation for SGD

Caching Placement and Resource Allocation for Cache-Enabling UAV NOMA Networks

Contact Info

Product

Resources

About