In this paper,we consider the distributed online optimization problem on a time-varying network,where each agent on the network has its own time-varying objective function and the goal is to minimize the overall loss ...In this paper,we consider the distributed online optimization problem on a time-varying network,where each agent on the network has its own time-varying objective function and the goal is to minimize the overall loss accumulated.Moreover,we focus on distributed algorithms which do not use gradient information and projection operators to improve the applicability and computational efficiency.By introducing the deterministic differences and the randomized differences to substitute the gradient information of the objective functions and removing the projection operator in the traditional algorithms,we design two kinds of gradient-free distributed online optimization algorithms without projection step,which can economize considerable computational resources as well as has less limitations on the applicability.We prove that both of two algorithms achieves consensus of the estimates and regrets of\(O\left(\log(T)\right)\)for local strongly convex objective,respectively.Finally,a simulation example is provided to verify the theoretical results.展开更多
A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R...A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R_(X)(φ)is applied on the single-qubit binary quantum classifier,and the training data and parameters are loaded intoφin the form of vector multiplication.The cost function is decreased by finding the value of each parameter that yields the minimum expectation value of measuring the quantum circuit.The algorithm is performed iteratively for all parameters one by one until the cost function satisfies the stop condition.The proposed GFO-based SQC is demonstrated for classification tasks in Iris and MNIST datasets and compared with the Adam-based SQC and the quantum support vector machine(QSVM).Furthermore,the performance of the GFO-based SQC is discussed when the rotation gate in the quantum device is under different types of noise.The simulation results show that the GFO-based SQC can reach a high accuracy in reduced time.Additionally,the proposed GFO algorithm can quickly complete the training process of the SQC.Importantly,the GFO-based SQC has a good performance in noisy environments.展开更多
This paper focuses on the online distributed optimization problem based on multi-agent systems. In this problem, each agent can only access its own cost function and a convex set, and can only exchange local state inf...This paper focuses on the online distributed optimization problem based on multi-agent systems. In this problem, each agent can only access its own cost function and a convex set, and can only exchange local state information with its current neighbors through a time-varying digraph. In addition, the agents do not have access to the information about the current cost functions until decisions are made. Different from most existing works on online distributed optimization, here we consider the case where the cost functions are strongly pseudoconvex and real gradients of the cost functions are not available. To handle this problem, a random gradient-free online distributed algorithm involving the multi-point gradient estimator is proposed. Of particular interest is that under the proposed algorithm, each agent only uses the estimation information of gradients instead of the real gradient information to make decisions. The dynamic regret is employed to measure the proposed algorithm. We prove that if the cumulative deviation of the minimizer sequence grows within a certain rate, then the expectation of dynamic regret increases sublinearly. Finally, a simulation example is given to corroborate the validity of our results.展开更多
A Gray code based gradient-free optimization(GCO)algorithm is proposed to update the parameters of parameterized quantum circuits(PQCs)in this work.Each parameter of PQCs is encoded as a binary string,named as a gene,...A Gray code based gradient-free optimization(GCO)algorithm is proposed to update the parameters of parameterized quantum circuits(PQCs)in this work.Each parameter of PQCs is encoded as a binary string,named as a gene,and a genetic-based method is adopted to select the offsprings.The individuals in the offspring are decoded in Gray code way to keep Hamming distance,and then are evaluated to obtain the best one with the lowest cost value in each iteration.The algorithm is performed iteratively for all parameters one by one until the cost value satisfies the stop condition or the number of iterations is reached.The GCO algorithm is demonstrated for classification tasks in Iris and MNIST datasets,and their performance are compared by those with the Bayesian optimization algorithm and binary code based optimization algorithm.The simulation results show that the GCO algorithm can reach high accuracies steadily for quantum classification tasks.Importantly,the GCO algorithm has a robust performance in the noise environment.展开更多
为解决一类有向拓扑结构下模型未知的非线性多智能体系统的聚类一致性问题,考虑到传统无模型自适应控制(MFAC)算法中存在的收敛速度慢等问题,提出了一种基于梯度下降的无模型聚类一致性控制算法。首先,在无模型算法中引入自适应矩估计(a...为解决一类有向拓扑结构下模型未知的非线性多智能体系统的聚类一致性问题,考虑到传统无模型自适应控制(MFAC)算法中存在的收敛速度慢等问题,提出了一种基于梯度下降的无模型聚类一致性控制算法。首先,在无模型算法中引入自适应矩估计(adaptive moment estimation,Adam)梯度下降优化方法,利用梯度的矩估计自适应地调整学习率并更新MFAC中的伪偏导数,加快并提高了模型的准确性。然后,在系统拓扑结构和聚类耦合强度约束下定义多智能体聚类误差。在此基础上,设计了基于Adam-MFAC的多智能体聚类一致性控制协议。此外,对Adam-MFAC方法的稳定性和收敛性进行了分析和证明。最后,分别考虑了具有固定拓扑和切换拓扑的系统,对所提出的方法进行仿真,证明了所提出的控制策略在多智能体聚类一致性问题上的有效性和优越性。展开更多
The closed-loop reservoir management technique enables a dynamic and real-time optimal production schedule under the existing reservoir conditions to be achieved by adjusting the injection and production strategies. T...The closed-loop reservoir management technique enables a dynamic and real-time optimal production schedule under the existing reservoir conditions to be achieved by adjusting the injection and production strategies. This is one of the most effective ways to exploit limited oil reserves more economically and efficiently. There are two steps in closed-loop reservoir management： automatic history matching and reservoir production opti- mization. Both of the steps are large-scale complicated optimization problems. This paper gives a general review of the two basic techniques in closed-loop reservoir man- agement; summarizes the applications of gradient-based algorithms, gradient-free algorithms, and artificial intelligence algorithms; analyzes the characteristics and application conditions of these optimization methods; and finally discusses the emphases and directions of future research on both automatic history matching and reservoir production optimization.展开更多
How to fit a properly nonlinear classification model from conventional well logs to lithofacies is a key problem for machine learning methods.Kernel methods(e.g.,KFD,SVM,MSVM)are effective attempts to solve this issue...How to fit a properly nonlinear classification model from conventional well logs to lithofacies is a key problem for machine learning methods.Kernel methods(e.g.,KFD,SVM,MSVM)are effective attempts to solve this issue due to abilities of handling nonlinear features by kernel functions.Deep mining of log features indicating lithofacies still needs to be improved for kernel methods.Hence,this work employs deep neural networks to enhance the kernel principal component analysis(KPCA)method and proposes a deep kernel method(DKM)for lithofacies identification using well logs.DKM includes a feature extractor and a classifier.The feature extractor consists of a series of KPCA models arranged according to residual network structure.A gradient-free optimization method is introduced to automatically optimize parameters and structure in DKM,which can avoid complex tuning of parameters in models.To test the validation of the proposed DKM for lithofacies identification,an open-sourced dataset with seven con-ventional logs(GR,CAL,AC,DEN,CNL,LLD,and LLS)and lithofacies labels from the Daniudi Gas Field in China is used.There are eight lithofacies,namely clastic rocks(pebbly,coarse,medium,and fine sand-stone,siltstone,mudstone),coal,and carbonate rocks.The comparisons between DKM and three commonly used kernel methods(KFD,SVM,MSVM)show that(1)DKM(85.7%)outperforms SVM(77%),KFD(79.5%),and MSVM(82.8%)in accuracy of lithofacies identification;(2)DKM is about twice faster than the multi-kernel method(MSVM)with good accuracy.The blind well test in Well D13 indicates that compared with the other three methods DKM improves about 24%in accuracy,35%in precision,41%in recall,and 40%in F1 score,respectively.In general,DKM is an effective method for complex lithofacies identification.This work also discussed the optimal structure and classifier for DKM.Experimental re-sults show that(m_(1),m_(2),O)is the optimal model structure and linear svM is the optimal classifier.(m_(1),m_(2),O)means there are m KPCAs,and then m2 residual units.A workflow to determine an optimal classifier in DKM for lithofacies identification is proposed,too.展开更多
文摘In this paper,we consider the distributed online optimization problem on a time-varying network,where each agent on the network has its own time-varying objective function and the goal is to minimize the overall loss accumulated.Moreover,we focus on distributed algorithms which do not use gradient information and projection operators to improve the applicability and computational efficiency.By introducing the deterministic differences and the randomized differences to substitute the gradient information of the objective functions and removing the projection operator in the traditional algorithms,we design two kinds of gradient-free distributed online optimization algorithms without projection step,which can economize considerable computational resources as well as has less limitations on the applicability.We prove that both of two algorithms achieves consensus of the estimates and regrets of\(O\left(\log(T)\right)\)for local strongly convex objective,respectively.Finally,a simulation example is provided to verify the theoretical results.
基金Project supported by the National Natural Science Foundation of China(Grant No.62375140)Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX190900)。
文摘A single-qubit quantum classifier(SQC)based on a gradient-free optimization(GFO)algorithm,named the GFO-based SQC,is proposed to overcome the effects of barren plateaus caused by quantum devices.Here,a rotation gate R_(X)(φ)is applied on the single-qubit binary quantum classifier,and the training data and parameters are loaded intoφin the form of vector multiplication.The cost function is decreased by finding the value of each parameter that yields the minimum expectation value of measuring the quantum circuit.The algorithm is performed iteratively for all parameters one by one until the cost function satisfies the stop condition.The proposed GFO-based SQC is demonstrated for classification tasks in Iris and MNIST datasets and compared with the Adam-based SQC and the quantum support vector machine(QSVM).Furthermore,the performance of the GFO-based SQC is discussed when the rotation gate in the quantum device is under different types of noise.The simulation results show that the GFO-based SQC can reach a high accuracy in reduced time.Additionally,the proposed GFO algorithm can quickly complete the training process of the SQC.Importantly,the GFO-based SQC has a good performance in noisy environments.
基金supported by the National Natural Science Foundation of China(Nos.62103169,51875380)the China Postdoctoral Science Foundation(No.2021M691313).
文摘This paper focuses on the online distributed optimization problem based on multi-agent systems. In this problem, each agent can only access its own cost function and a convex set, and can only exchange local state information with its current neighbors through a time-varying digraph. In addition, the agents do not have access to the information about the current cost functions until decisions are made. Different from most existing works on online distributed optimization, here we consider the case where the cost functions are strongly pseudoconvex and real gradients of the cost functions are not available. To handle this problem, a random gradient-free online distributed algorithm involving the multi-point gradient estimator is proposed. Of particular interest is that under the proposed algorithm, each agent only uses the estimation information of gradients instead of the real gradient information to make decisions. The dynamic regret is employed to measure the proposed algorithm. We prove that if the cumulative deviation of the minimizer sequence grows within a certain rate, then the expectation of dynamic regret increases sublinearly. Finally, a simulation example is given to corroborate the validity of our results.
基金This work was supported by the National Natural Science Foundation of China(Grant Nos.61871234 and 62375140)Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX190900).
文摘A Gray code based gradient-free optimization(GCO)algorithm is proposed to update the parameters of parameterized quantum circuits(PQCs)in this work.Each parameter of PQCs is encoded as a binary string,named as a gene,and a genetic-based method is adopted to select the offsprings.The individuals in the offspring are decoded in Gray code way to keep Hamming distance,and then are evaluated to obtain the best one with the lowest cost value in each iteration.The algorithm is performed iteratively for all parameters one by one until the cost value satisfies the stop condition or the number of iterations is reached.The GCO algorithm is demonstrated for classification tasks in Iris and MNIST datasets,and their performance are compared by those with the Bayesian optimization algorithm and binary code based optimization algorithm.The simulation results show that the GCO algorithm can reach high accuracies steadily for quantum classification tasks.Importantly,the GCO algorithm has a robust performance in the noise environment.
文摘为解决一类有向拓扑结构下模型未知的非线性多智能体系统的聚类一致性问题,考虑到传统无模型自适应控制(MFAC)算法中存在的收敛速度慢等问题,提出了一种基于梯度下降的无模型聚类一致性控制算法。首先,在无模型算法中引入自适应矩估计(adaptive moment estimation,Adam)梯度下降优化方法,利用梯度的矩估计自适应地调整学习率并更新MFAC中的伪偏导数,加快并提高了模型的准确性。然后,在系统拓扑结构和聚类耦合强度约束下定义多智能体聚类误差。在此基础上,设计了基于Adam-MFAC的多智能体聚类一致性控制协议。此外,对Adam-MFAC方法的稳定性和收敛性进行了分析和证明。最后,分别考虑了具有固定拓扑和切换拓扑的系统,对所提出的方法进行仿真,证明了所提出的控制策略在多智能体聚类一致性问题上的有效性和优越性。
基金the Important National Science & Technology Specific Projects of China (Grant No. 2011ZX05024-004)the Natural Science Foundation for Distinguished Young Scholars of Shandong Province, China (Grant No. JQ201115)+2 种基金the Program for New Century Excellent Talents in University (Grant No. NCET-11-0734)the Fundamental Research Funds for the Central Universities (Grant No. 13CX05007A, 13CX05016A)the Program for Changjiang Scholars and Innovative Research Team in University (IRT1294)
文摘The closed-loop reservoir management technique enables a dynamic and real-time optimal production schedule under the existing reservoir conditions to be achieved by adjusting the injection and production strategies. This is one of the most effective ways to exploit limited oil reserves more economically and efficiently. There are two steps in closed-loop reservoir management： automatic history matching and reservoir production opti- mization. Both of the steps are large-scale complicated optimization problems. This paper gives a general review of the two basic techniques in closed-loop reservoir man- agement; summarizes the applications of gradient-based algorithms, gradient-free algorithms, and artificial intelligence algorithms; analyzes the characteristics and application conditions of these optimization methods; and finally discusses the emphases and directions of future research on both automatic history matching and reservoir production optimization.
基金supported by the National Natural Science Foundation of China(Grant No.42002134)China Postdoctoral Science Foundation(Grant No.2021T140735)Science Foundation of China University of Petroleum,Beijing(Grant Nos.2462020XKJS02 and 2462020YXZZ004).
文摘How to fit a properly nonlinear classification model from conventional well logs to lithofacies is a key problem for machine learning methods.Kernel methods(e.g.,KFD,SVM,MSVM)are effective attempts to solve this issue due to abilities of handling nonlinear features by kernel functions.Deep mining of log features indicating lithofacies still needs to be improved for kernel methods.Hence,this work employs deep neural networks to enhance the kernel principal component analysis(KPCA)method and proposes a deep kernel method(DKM)for lithofacies identification using well logs.DKM includes a feature extractor and a classifier.The feature extractor consists of a series of KPCA models arranged according to residual network structure.A gradient-free optimization method is introduced to automatically optimize parameters and structure in DKM,which can avoid complex tuning of parameters in models.To test the validation of the proposed DKM for lithofacies identification,an open-sourced dataset with seven con-ventional logs(GR,CAL,AC,DEN,CNL,LLD,and LLS)and lithofacies labels from the Daniudi Gas Field in China is used.There are eight lithofacies,namely clastic rocks(pebbly,coarse,medium,and fine sand-stone,siltstone,mudstone),coal,and carbonate rocks.The comparisons between DKM and three commonly used kernel methods(KFD,SVM,MSVM)show that(1)DKM(85.7%)outperforms SVM(77%),KFD(79.5%),and MSVM(82.8%)in accuracy of lithofacies identification;(2)DKM is about twice faster than the multi-kernel method(MSVM)with good accuracy.The blind well test in Well D13 indicates that compared with the other three methods DKM improves about 24%in accuracy,35%in precision,41%in recall,and 40%in F1 score,respectively.In general,DKM is an effective method for complex lithofacies identification.This work also discussed the optimal structure and classifier for DKM.Experimental re-sults show that(m_(1),m_(2),O)is the optimal model structure and linear svM is the optimal classifier.(m_(1),m_(2),O)means there are m KPCAs,and then m2 residual units.A workflow to determine an optimal classifier in DKM for lithofacies identification is proposed,too.
