Accelerated Primal-Dual Projection Neurodynamic Approach With Time Scaling for Linear and Set Constrained Convex Optimization Problems

The Nesterov accelerated dynamical approach serves as an essential tool for addressing convex optimization problems with accelerated convergence rates.Most previous studies in this field have primarily concentrated on unconstrained smooth con-vex optimization problems.In this paper,on the basis of primal-dual dynamical approach,Nesterov accelerated dynamical approach,projection operator and directional gradient,we present two accelerated primal-dual projection neurodynamic approaches with time scaling to address convex optimization problems with smooth and nonsmooth objective functions subject to linear and set constraints,which consist of a second-order ODE(ordinary differential equation)or differential conclusion system for the primal variables and a first-order ODE for the dual vari-ables.By satisfying specific conditions for time scaling,we demonstrate that the proposed approaches have a faster conver-gence rate.This only requires assuming convexity of the objective function.We validate the effectiveness of our proposed two accel-erated primal-dual projection neurodynamic approaches through numerical experiments.

Performance Analysis of Sparse Array based Massive MIMO via Joint Convex Optimization

Massive multiple-input multiple-output(MIMO)technology enables higher data rate transmission in the future mobile communications.However,exploiting a large number of antenna elements at base station(BS)makes effective implementation of massive MIMO challenging,due to the size and weight limits of the masssive MIMO that are located on each BS.Therefore,in order to miniaturize the massive MIMO,it is crucial to reduce the number of antenna elements via effective methods such as sparse array synthesis.In this paper,a multiple-pattern synthesis is considered towards convex optimization(CO).The joint convex optimization(JCO)based synthesis is proposed to construct a codebook for beamforming.Then,a criterion containing multiple constraints is developed,in which the sparse array is required to fullfill all constraints.Finally,extensive evaluations are performed under realistic simulation settings.The results show that with the same number of antenna elements,sparse array using the proposed JCO-based synthesis outperforms not only the uniform array,but also the sparse array with the existing CO-based synthesis method.Furthermore,with a half of the number of antenna elements that on the uniform array,the performance of the JCO-based sparse array approaches to that of the uniform array.

A new primal-dual path-following interior-point algorithm for linearly constrained convex optimization

In this paper, a primal-dual path-following interior-point algorithm for linearly constrained convex optimization(LCCO) is presented.The algorithm is based on a new technique for finding a class of search directions and the strategy of the central path.At each iteration, only full-Newton steps are used.Finally, the favorable polynomial complexity bound for the algorithm with the small-update method is deserved, namely, O(√n log n /ε).

Stabilization of linear time-varying systems with state and input constraints using convex optimization

The stabilization problem of linear time-varying systems with both state and input constraints is considered. Sufficient conditions for the existence of the solution to this problem are derived and a gain-switched（gain-scheduled） state feedback control scheme is built to stabilize the constrained timevarying system. The design problem is transformed to a series of convex feasibility problems which can be solved efficiently. A design example is given to illustrate the effect of the proposed algorithm.

A Regularized Newton Method with Correction for Unconstrained Convex Optimization

In this paper, we present a regularized Newton method (M-RNM) with correction for minimizing a convex function whose Hessian matrices may be singular. At every iteration, not only a RNM step is computed but also two correction steps are computed. We show that if the objective function is LC2, then the method posses globally convergent. Numerical results show that the new algorithm performs very well.

A novel image segmentation approach for wood plate surface defect classification through convex optimization

Detection of wood plate surface defects using image processing is a complicated problem in the forest industry as the image of the wood surface contains different kinds of defects. In order to obtain complete defect images, we used convex optimization(CO) with different weights as a pretreatment method for smoothing and the Otsu segmentation method to obtain the target defect area images. Structural similarity(SSIM) results between original image and defect image were calculated to evaluate the performance of segmentation with different convex optimization weights. The geometric and intensity features of defects were extracted before constructing a classification and regression tree(CART) classifier. The average accuracy of the classifier is 94.1% with four types of defects on Xylosma congestum wood plate surface: pinhole, crack,live knot and dead knot. Experimental results showed that CO can save the edge of target defects maximally, SSIM can select the appropriate weight for CO, and the CART classifier appears to have the advantages of good adaptability and high classification accuracy.

Learning Convex Optimization Models

A convex optimization model predicts an output from an input by solving a convex optimization problem.The class of convex optimization models is large,and includes as special cases many well-known models like linear and logistic regression.We propose a heuristic for learning the parameters in a convex optimization model given a dataset of input-output pairs,using recently developed methods for differentiating the solution of a convex optimization problem with respect to its parameters.We describe three general classes of convex optimization models,maximum a posteriori(MAP)models,utility maximization models,and agent models,and present a numerical experiment for each.

Multiconstraint adaptive three-dimensional guidance law using convex optimization

The traditional guidance law only guarantees the accuracy of attacking a target. However, the look angle and acceleration constraints are indispensable in applications. A new adaptive three-dimensional proportional navigation(PN) guidance law is proposed based on convex optimization. Decomposition of the three-dimensional space is carried out to establish threedimensional kinematic engagements. The constraints and the performance index are disposed by using the convex optimization method. PN guidance gains can be obtained by solving the optimization problem. This solution is more rapid and programmatic than the traditional method and provides a foundation for future online guidance methods, which is of great value for engineering applications.

Computation of Peak Output for Inputs Restricted in L_2 and L_∞ Norms Using Finite Difference Schemes and Convex Optimization

Control systems designed by the principle of matching gives rise to problems of evaluating the peak output. This paper proposes a practical method for computing the peak output of linear time-invariant and non-anticipative systems for a class of possible sets that are characterized with many bounding conditions on the two- and/or the infinity-norms of the inputs and their derivatives. The original infinite-dimensional convex optimization problem is approximated as a large-scale convex programme defined in a Euclidean space, which are associated with sparse matrices and thus can be solved efficiently in practice. The numerical results show that the method performs satisfactorily, and that using a possible set with many bounding conditions can help to reduce the design conservatism and thereby yield a better match.

The Application of Convex Optimization to Load Optimal Allocation in a Single Workstation System

The service quality of a workstation depends mainly on its service load, ifnot taking into account all kinds of devices' break-downs. In this article, an optimization modelwith inequality constraints is proposed, which aims to minimize the service load. A noveltransformation of optimization variables is also devised and the constraints are properly combinedso as to make this model into a convex one, whose corresponding Lagrange function and the KKTconditions are established afterwards. The interior-point method for convex optimization ispresented here as an efficient computation tool. Finally, this model is evaluated by a real example,from which conclusions are reached that the interior-point method possesses advantages such asfaster convergeoce and fewer iterations and it is possible to make complicated nonlinearoptimization problems exhibit convexity so as to obtain the optimum.

An Introduction to Convex Optimization Theory in Communication Signals Recognition

In this paper,convex optimization theory is introduced into the recognition of communication signals. The detailed content contains three parts. The first part gives a survey of basic concepts,main technology and recognition model of convex optimization theory. Special emphasis is placed on how to set up the new recognition model of communication signals with multisensor reports. The second part gives the solution method of the recognition model,which is called Logarithmic Penalty Barrier Function. The last part gives several numeric simulations,in contrast to D-S evidence inference method,this new method can also generate reasonable recognition results. Moreover,this new method can deal with the form of sensor reports which is more general than that allowed by the D-S evidence inference method,and it has much lower computation complexity than that of D-S evidence inference method. In addition,this new method has better recognition result,stronger anti-interference and robustness. Therefore,the convex optimization methods can be widely used in the recognition of communication signals.

DOWNWARD LOOKING SPARSE LINEAR ARRAY 3D SAR IMAGING ALGORITHM BASED ON BACK-PROJECTION AND CONVEX OPTIMIZATION

Downward Looking Sparse Linear Array Three Dimensional SAR(DLSLA 3D SAR) is an important form of 3D SAR imaging, which has a widespread application field. Since its practical equivalent phase centers are usually distributed sparsely and nonuniformly, traditional 3D SAR algorithms suffer from low resolution and high sidelobes in cross-track dimension. To deal with this problem, this paper introduces a method based on back-projection and convex optimization to achieve 3D high accuracy imaging reconstruction. Compared with traditional SAR algorithms, the proposed method sufficiently utilizes the sparsity of the 3D SAR imaging scene and can achieve lower sidelobes and higher resolution in cross-track dimension. In the simulated experiments, the reconstructed results of both simple and complex imaging scene verify that the proposed method outperforms 3D back-projection algorithm and shows satisfying cross-track dimensional resolution and good robustness to noise.

Application of Convex Optimization to Queuing Systems

On the basis of the queuing theory, a nonlinear optimal load allocation model is proposed. A novel transformafion method for the optimization variables is also presented, and the constraints are properly combined so as to make this model convex. The interior-point method for convex optimization is presented as an efficient computational tool. Finally, this model is evaluated by a real example,from which the following conclusions are drawn： the optimum result can ensure the full utilization of machines and the smallest amount of WIP （work-in-progress） in queuing systems; the interior-point method needs a few iterations with significant computational savings; other performance measures of queuing systems can also be optimized in a similar way.

Research on Optimizing Computer Network Structure based on Genetic Algorithm and Modified Convex Optimization Theory

In this paper, we report in-depth analysis and research on the optimizing computer network structure based on genetic algorithm and modified convex optimization theory. Machine learning method has been widely used in the background and one of its core problems is to solve the optimization problem. Unlike traditional batch algorithm, stochastic gradient descent algorithm in each iteration calculation, the optimization of a single sample point only losses could greatly reduce the memory overhead. The experiment illustrates the feasibility of our proposed approach.

Optimal tracking control for linear time-delay large-scale systems with persistent disturbances

An optimal tracking control （OTC） problem for linear time-delay large-scale systems affected by external persistent disturbances is investigated. Based on the internal model principle, a disturbance compensator is constructed. The system with persistent disturbances is transformed into an augmented system without persistent disturbances. The original OTC problem of linear time-delay system is transformed into a sequence of linear two- point boundary value （TPBV） problems by introducing a sensitivity parameter and expanding Maclaurin series around it. By solving an OTC law of the augmented system, the OTC law of the original system is obtained. A numerical simulation is provided to illustrate the effectiveness of the proposed method.

NEW DESIGN OF ROBUST OPTIMAL ARBITRARY TIME-DELAY FILTER

Zero placement method in the frequency domain is utilized to design robust multi-hump EI optimal arbitrary time-delay filter （OATF） by placing two or more filter zeros near the system poles. A total insensitive OATF can be also achieved if the problem of insensitivity to damping errors is considered. This design strategy is easier to derive and implement. Applications in the anti-swing control of overhead cranes verify the fine performance of this strategy. A better suppression of the load vibrations is obtained using the proposed new OATF, which is more robust to the variation of the cable length.

Optimal disturbances rejection control for singularly perturbed systems with time-delay

The optimal control design for singularly perturbed time-delay systems affected by external distur-bances is considered.Based on the decomposition theory of singular perturbation,the system is decom-posed into a fast subsystem without time-delay and a slow time-delay subsystem with disturbances.Theoptimal disturbances rejection control law of the slow subsystem is obtained by using the successive ap-proximation approach(SAA)and feedforward compensation method.Further,the feedforward and feed-back composite control(FFCC)law for the original problem is developed.The FFCC law consists of lin-ear analytic terms and a time-delay compensation term which is the limit of the solution sequence of theadjoint vector equations.A disturbance observer is introduced to make the FFCC law physically realiz-able.Numerical examples show that the proposed algorithm is effective.

Optimal Control for Time-Delay Bilinear Systems with Sinusoidal Disturbances

This paper considers the optimal control problem for time-delay bilinear systems affected by sinusoidal disturbances with known frequency and measurable amplitude and phase. Firstly, using the differential homeomorphism, a time-delay bilinear system affected by sinusoidal disturbances is changed to a time-delay pseudo linear system through the coordinate transformation. Then the system with time-delay in control variable is transformed to a linear controllable system without delay using model transformation. At last based on the theory of linear quadratic optimal control, an optimal control law which is used to eliminate the influence of the disturbances is derived from a Riccati equation and Matrix equations. The simulation results show the effectiveness of the method.

Distributed Stochastic Optimization with Compression for Non-Strongly Convex Objectives

We are investigating the distributed optimization problem,where a network of nodes works together to minimize a global objective that is a finite sum of their stored local functions.Since nodes exchange optimization parameters through the wireless network,large-scale training models can create communication bottlenecks,resulting in slower training times.To address this issue,CHOCO-SGD was proposed,which allows compressing information with arbitrary precision without reducing the convergence rate for strongly convex objective functions.Nevertheless,most convex functions are not strongly convex(such as logistic regression or Lasso),which raises the question of whether this algorithm can be applied to non-strongly convex functions.In this paper,we provide the first theoretical analysis of the convergence rate of CHOCO-SGD on non-strongly convex objectives.We derive a sufficient condition,which limits the fidelity of compression,to guarantee convergence.Moreover,our analysis demonstrates that within the fidelity threshold,this algorithm can significantly reduce transmission burden while maintaining the same convergence rate order as its no-compression equivalent.Numerical experiments further validate the theoretical findings by demonstrating that CHOCO-SGD improves communication efficiency and keeps the same convergence rate order simultaneously.And experiments also show that the algorithm fails to converge with low compression fidelity and in time-varying topologies.Overall,our study offers valuable insights into the potential applicability of CHOCO-SGD for non-strongly convex objectives.Additionally,we provide practical guidelines for researchers seeking to utilize this algorithm in real-world scenarios.

General Lyapunov Stability and Its Application to Time-Varying Convex Optimization

In this article, a general Lyapunov stability theory of nonlinear systems is put forward and it contains asymptotic/finite-time/fast finite-time/fixed-time stability. Especially, a more accurate estimate of the settling-time function is exhibited for fixedtime stability, and it is still extraneous to the initial conditions.This can be applied to obtain less conservative convergence time of the practical systems without the information of the initial conditions. As an application, the given fixed-time stability theorem is used to resolve time-varying(TV) convex optimization problem.By the Newton's method, two classes of new dynamical systems are constructed to guarantee that the solution of the dynamic system can track to the optimal trajectory of the unconstrained and equality constrained TV convex optimization problems in fixed time, respectively. Without the exact knowledge of the time derivative of the cost function gradient, a fixed-time dynamical non-smooth system is established to overcome the issue of robust TV convex optimization. Two examples are provided to illustrate the effectiveness of the proposed TV convex optimization algorithms. Subsequently, the fixed-time stability theory is extended to the theories of predefined-time/practical predefined-time stability whose bound of convergence time can be arbitrarily given in advance, without tuning the system parameters. Under which, TV convex optimization problem is solved. The previous two examples are used to demonstrate the validity of the predefined-time TV convex optimization algorithms.