Distributed gradient descent method with edge‐based event‐driven communication for non‐convex optimization

Adachi, Takafumi; Hayashi, Naoki; Takai, Shigemasa

doi:10.1049/cth2.12127

Cited by 16 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e method can be divided into three categories, namely batch gradient descent, mini-batch gradient descent, and stochastic gradient descent [22].…”

Section: Head Chunk Track Chunkmentioning

confidence: 99%

“…By using this algorithm, it is relatively easy to obtain the optimal solution for the function that needs to be trained, thereby improving the accuracy of the model. The method can be divided into three categories, namely batch gradient descent, mini-batch gradient descent, and stochastic gradient descent [ 22 ].…”

Section: Introduction Of Related Algorithms and Model Establishment A...mentioning

confidence: 99%

See 1 more Smart Citation

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology

Jian¹,

Zhang³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In order to improve the accuracy and precision of music generation assisted by robotics, this study analyzes the application of deep learning in piano music generation. Firstly, based on the basic concepts of robotics and deep learning, the advantages of long short-term memory (LSTM) networks are introduced and applied to the piano music generation. Meanwhile, based on LSTM, dropout coefficients are used for optimization. Secondly, various parameters of the algorithm are determined, including the effects of the number of iterations and neurons in the hidden layer on the effect of piano music generation. Finally, the generated music sequence spectrograms are analyzed to illustrate the accuracy and rationality of the algorithm. The spectrograms are compared with the music sequence spectrograms generated by the traditional restricted Boltzmann machine (RBM) music generation algorithm. The results show that (1) when the dropout coefficient value is 0.7, the function converges faster, and the experimental results are better; (2) when the number of iterations is 6000, the error between the generated music sequence and the original music is the smallest; (3) the number of hidden layers of the network is set to 4. When the number of neurons in each hidden layer is set to 1024, the training result of the network is optimal; (4) compared with the traditional RBM piano music generation algorithm, the LSTM-based algorithm and the sampling frequency distribution tend to be consistent with the original sample. The results show that the network has good performance in music generation and can provide a certain reference for automatic music generation.

show abstract

“…e method can be divided into three categories, namely batch gradient descent, mini-batch gradient descent, and stochastic gradient descent [22].…”

Section: Head Chunk Track Chunkmentioning

confidence: 99%

Section: Introduction Of Related Algorithms and Model Establishment A...mentioning

confidence: 99%

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology

Jian¹,

Zhang³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…On the other hand, the event-driven communication policy sends an estimated optimal solution to a neighboring provider only when an error of the estimated solution exceeds a certain threshold [28,29]. A distributed optimization algorithm based on event-driven communication has been investigated to reduce the number of communications between agents and effectively use network resources [30][31][32][33][34][35][36].…”

Section: Related Workmentioning

confidence: 99%

Communication‐aware distributed rebalancing for cooperative car‐sharing service

Hayashi

Sakurama

2022

IET Control Theory & Appl

View full text Add to dashboard Cite

This study presents a cooperative car‐sharing system in which various service providers jointly operate a sharing service. A distributed algorithm is proposed for rebalancing control to reduce deadhead vehicles as much as possible under the constraints of dispatchable vehicles and parking slots at car stations. Each provider cooperatively searches for the optimal solution by exchanging the estimated values of the optimal dual solutions over the communication networks between providers. Event‐driven communication is considered in which information exchange with the neighboring providers is performed only when the amount of change of the estimated optimal dual solution exceeds a threshold. Numerical instances explain that the estimations of all service providers meet the optimal rebalancing solutions.

show abstract

“…A quadratic optimization problem considered in [23] and a continuous-time algorithm with event-triggered communication is proposed to solve it. In [24], nonconvex optimization problems are addressed by implementing an event-triggered communication on the scheme of the distributed gradient descent method. The existing discrete-time algorithm from which we take inspiration is the so-called gradient tracking algorithm.…”

Section: Introductionmentioning

confidence: 99%

Triggered Gradient Tracking for Asynchronous Distributed Optimization

Carnevale¹,

Notarnicola²,

Marconi³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper proposes ASYNCHRONOUS TRIGGERED GRADIENT TRACKING, i.e., a distributed optimization algorithm to solve consensus optimization over networks with asynchronous communication. As a building block, we start by devising the continuous-time counterpart of the recently proposed (discretetime) distributed gradient tracking called CONTINUOUS GRA-DIENT TRACKING. By using a Lyapunov approach, we prove exponential stability of the equilibrium corresponding to agents' estimates being consensual to the optimal solution of the problem, with arbitrary initialization of the local estimates. Then, we propose two triggered versions of the algorithm. In the first one, the agents continuously integrate their local dynamics and exchange with neighbors current local variables according to a synchronous communication protocol. In ASYNCHRONOUS TRIGGERED GRADIENT TRACKING, we propose a totally asynchronous scheme in which each agent sends to neighbors its current local variables based on a triggering condition that depends on a locally verifiable condition. The triggering protocol preserves the linear convergence of the algorithm and excludes the Zeno behavior. By using the stability analysis of CONTINUOUS GRADIENT TRACKING as a preparatory result, we show exponential stability of the equilibrium point holds for both triggered algorithms and any estimates' initialization. Finally, numerical simulations validate the effectiveness of the proposed methods on a data analytics problem, showing also the improved performance in terms of inter-agent communication.

show abstract

Distributed gradient descent method with edge‐based event‐driven communication for non‐convex optimization

Cited by 16 publications

References 33 publications

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology

Communication‐aware distributed rebalancing for cooperative car‐sharing service

Triggered Gradient Tracking for Asynchronous Distributed Optimization

Contact Info

Product

Resources

About