This paper considers online classification learning algorithms for regularized classification schemes with generalized gradient. A novel capacity independent approach is presented. It verifies the strong convergence o...This paper considers online classification learning algorithms for regularized classification schemes with generalized gradient. A novel capacity independent approach is presented. It verifies the strong convergence of sizes and yields satisfactory convergence rates for polynomially decaying step sizes. Compared with the gradient schemes, this al- gorithm needs only less additional assumptions on the loss function and derives a stronger result with respect to the choice of step sizes and the regularization parameters.展开更多
Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inp...Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural networks.In this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training RVFL.The link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is analyzed.The experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.展开更多
This paper presents an online integral reinforcement learning(RL)solution for problems with hierarchy decision makers.Specifically,we reformulate this model as a leaderfollower game,in which control input and determin...This paper presents an online integral reinforcement learning(RL)solution for problems with hierarchy decision makers.Specifically,we reformulate this model as a leaderfollower game,in which control input and deterministic disturbance act as decision makers at different levels of hierarchy:The control input plays the role of the leader,while the disturbance plays the role of the follower.The main contributions of this paper can be summarized as follows.First,we introduce online RL to deal with systems that have partially unknown information,meaning that accurate dynamic information is not required.Second,we solve the leader-follower coupled Hamilton-Jacobi(HJ)and Riccati equations approximately online using the derived algorithm.Third,we provide turning laws for cost functions and controllers,which ensure closed-loop stability simultaneously.展开更多
We design online algorithms to schedule unit-length packets with values and deadlines through an unreliable communication channel. In this model, time is discrete. Packets arrive over time; each packet has a non-negat...We design online algorithms to schedule unit-length packets with values and deadlines through an unreliable communication channel. In this model, time is discrete. Packets arrive over time; each packet has a non-negative value and an integer deadline. In each time step, at most one packet can be sent. The ratio of successfully delivering a packet depends on the channel＇s quality of reliability. The objective is to maximize the total value gained by delivering packets no later than their respective deadlines. In this paper, we conduct theoretical and empirical studies of online learning approaches for this model and a few of its variants. These online learning algorithms are analyzed in terms of external regret. We conclude that no online learning algorithms have constant regrets. Our online learning algorithms outperform online competitive algorithms in terms of algorithmic simplicity and running complexity. In general, these online learning algorithms work no worse than the best known competitive online algorithm for maximizing weighted throughput in practice.展开更多
文摘This paper considers online classification learning algorithms for regularized classification schemes with generalized gradient. A novel capacity independent approach is presented. It verifies the strong convergence of sizes and yields satisfactory convergence rates for polynomially decaying step sizes. Compared with the gradient schemes, this al- gorithm needs only less additional assumptions on the loss function and derives a stronger result with respect to the choice of step sizes and the regularization parameters.
基金supported by the Ministry of Science and Technology of China(2018AAA0101000,2017YFF0205306,WQ20141100198)the National Natural Science Foundation of China(91648117)。
文摘Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural networks.In this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training RVFL.The link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is analyzed.The experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.
基金supported by the Support Plan on Science and Technology for Youth Innovation of Universities in Shandong Province(No.2021KJ086)the National Natural Science Foundation of China(Nos.62003234 and 61873179)the National Natural Science Foundation of Shandong Province(No.ZR2020QF048).
文摘This paper presents an online integral reinforcement learning(RL)solution for problems with hierarchy decision makers.Specifically,we reformulate this model as a leaderfollower game,in which control input and deterministic disturbance act as decision makers at different levels of hierarchy:The control input plays the role of the leader,while the disturbance plays the role of the follower.The main contributions of this paper can be summarized as follows.First,we introduce online RL to deal with systems that have partially unknown information,meaning that accurate dynamic information is not required.Second,we solve the leader-follower coupled Hamilton-Jacobi(HJ)and Riccati equations approximately online using the derived algorithm.Third,we provide turning laws for cost functions and controllers,which ensure closed-loop stability simultaneously.
基金Supported by US National Science Foundation (Nos. CCF-0915681 and CCF-1146578)DARPA’s Mission-Resilient Clouds Program under Contract 1FA8650-11-C-7190
文摘We design online algorithms to schedule unit-length packets with values and deadlines through an unreliable communication channel. In this model, time is discrete. Packets arrive over time; each packet has a non-negative value and an integer deadline. In each time step, at most one packet can be sent. The ratio of successfully delivering a packet depends on the channel＇s quality of reliability. The objective is to maximize the total value gained by delivering packets no later than their respective deadlines. In this paper, we conduct theoretical and empirical studies of online learning approaches for this model and a few of its variants. These online learning algorithms are analyzed in terms of external regret. We conclude that no online learning algorithms have constant regrets. Our online learning algorithms outperform online competitive algorithms in terms of algorithmic simplicity and running complexity. In general, these online learning algorithms work no worse than the best known competitive online algorithm for maximizing weighted throughput in practice.
