Coordinate Descent Research Articles

TM-OKC: An Unsupervised Topic Model for Text in Online Knowledge Communities

Online knowledge communities (OKCs), such as question-and-answer sites, have become increasingly popular venues for knowledge sharing. Accordingly, it is necessary for researchers and practitioners to develop effective and efficient text analysis tools to understand the massive amount of user-generated content (UGC) on OKCs. Unsupervised topic modeling has been widely adopted to extract human-interpretable latent topics embedded in texts. These identified topics can be further used in subsequent analysis and managerial practices. However, existing generic topic models that assume documents are independent are inappropriate for analyzing OKCs where structural relationships exist between questions and answers. Thus, a new method is needed to fill this research gap. In this study, we propose a new topic model specifically designed for the text in OKCs. We make three primary contributions to the research on topic modeling in this context. First, we build a general and flexible Bayesian framework to explicitly model structural and temporal dependencies among texts. Second, we statistically demonstrate the approximate model inference using mean-field and coordinate ascent algorithms. Third, we showcase the practical value and relative merit of our method via a specific downstream task (i.e., user profiling). The proposed model is illustrated using two real-world datasets from well-known OKCs (i.e., Stack Exchange and Quora), and extensive experiments demonstrate its superiority over several cutting-edge benchmarks.

Bayesian L 1/2 Regression

It is well known that Bridge regression enjoys superior theoretical properties when compared to traditional LASSO. However, the current latent variable representation of its Bayesian counterpart, based on the exponential power prior, is computationally expensive in higher dimensions. In this article, we show that the exponential power prior has a closed form scale mixture of normal decomposition for α = ( 1 2 ) γ , γ ∈ { 1 , 2 , … } . We call these types of priors L 1 2 prior for short. We develop an efficient partially collapsed Gibbs sampling scheme for computation using the L 1 2 prior and study theoretical properties when p > n . In addition, we introduce a non-separable Bridge penalty function inspired by the fully Bayesian formulation and a novel, efficient coordinate descent algorithm. We prove the algorithm’s convergence and show that the local minimizer from our optimization algorithm has an oracle property. Finally, simulation studies were carried out to illustrate the performance of the new algorithms. Supplementary materials for this article are available online.

Stretched non-negative matrix factorization

A novel algorithm, stretchedNMF, is introduced for non-negative matrix factorization (NMF), accounting for signal stretching along the independent variable’s axis. It addresses signal variability caused by stretching, proving beneficial for analyzing data such as powder diffraction at varying temperatures. This approach provides a more meaningful decomposition, particularly when the component signals resemble those from chemical components in the sample. The stretchedNMF model introduces a stretching factor to accommodate signal expansion, solved using discretization and Block Coordinate Descent algorithms. Initial experimental results indicate that the stretchedNMF model outperforms conventional NMF for datasets exhibiting such expansion. An enhanced version, sparse-stretchedNMF, optimized for powder diffraction data from crystalline materials, leverages signal sparsity for accurate extraction, especially with small stretches. Experimental results showcase its effectiveness in analyzing diffraction data, including success in real-time chemical reaction experiments.

Joint vehicular power and RIS reflection coefficient optimization to maximize the minimum bit rate in VANETs

Reconfigurable intelligent surfaces (RISs) have recently gained significant attention for improving reliability in vehicular communications. However, ensuring reliable communication between far-distance vehicles remains a challenge. This work investigates an RIS-aided vehicular ad hoc network (VANET) in a road section where the distance between vehicles is too large for a single roadside unit (RSU) to provide reliable communication. We propose a novel RIS architecture where several RIS panels are connected by cables and each is equipped with a power amplifier. We then optimize vehicle power and RIS reflection coefficients to maximize the minimum bit rate of the VANET. Due to the non-convex nature of the formulated problem, we use fraction programming (FP) to reformulate it into a convex form, allowing solution using tools like CVX which is a MATLAB-based modeling system for convex optimization. The reformulated problem is then decoupled into subproblems. Block coordinate descent (BCD) is employed to optimize all variables alternately and obtain the joint optimal solution. Additionally, the alternating direction method of multipliers (ADMM) ensures that the phase shift of each reflecting element remains a unit vector. Finally, semidefinite relaxation (SDR) is used to solve the boolean quadratically constrained problem. Simulation results demonstrate the effectiveness of the proposed method and confirm that our architecture outperforms conventional approaches.

Energy Minimization for IRS-Assisted SWIPT-MEC System.

With the rapid development of the internet of things (IoT) era, IoT devices may face limitations in battery capacity and computational capability. Simultaneous wireless information and power transfer (SWIPT) and mobile edge computing (MEC) have emerged as promising technologies to address these challenges. Due to wireless channel fading and susceptibility to obstacles, this paper introduces intelligent reflecting surfaces (IRS) to enhance the spectral and energy efficiency of wireless networks. We propose a system model for IRS-assisted uplink offloading computation, downlink offloading computation results, and simultaneous energy transfer. Considering constraints such as IRS phase shifts, latency, energy harvesting, and offloading transmit power, we jointly optimize the CPU frequency of IoT devices, offloading transmit power, local computation workload, power splitting (PS) ratio, and IRS phase shifts. This establishes a multi-variate coupled nonlinear problem aimed at minimizing IoT devices energy consumption. We design an effective alternating optimization (AO) iterative algorithm based on block coordinate descent, and utilize closed-form solutions, Dinkelbach-based Lagrange dual method, and semidefinite relaxation (SDR) method to minimize IoT devices energy consumption. Simulation results demonstrate that the proposed scheme achieves lower energy consumption compared to other resource allocation strategies.

Joint optimization for energy efficient full-duplex UAV relaying with multiple user pairs

This paper investigates an unmanned aerial vehicle (UAV) assisted amplify-and-forward relaying, where a full-duplex (FD) fixed-wing UAV employs a time-division multiple access scheduling protocol to provide relay services for multiple source–destination user pairs. With the aim of maximizing energy efficiency (EE) of the system, a joint optimization problem is studied so as to jointly fulfill the communication scheduling of multiple user pairs, the transmit power control and the trajectory design of the UAV. Since the optimization variables of the problem are coupled, it is non-convex and hence hard to solve directly. To this end, the initial problem is decomposed into three subproblems corresponding to the optimization of communication scheduling, and transmit power and trajectory of the UAV, respectively. The three subproblems are solved by utilizing the linear programming, the successive convex approximation (SCA), and the Dinkelbach’s algorithm. Then an iterative algorithm based on the block coordinate descent technique is proposed to tackle the joint optimization problem by optimizing the three blocks of variables alternately. Simulation results demonstrate that the proposed algorithm converges efficiently, and the EE of the joint optimization scheme can be significantly improved compared to the benchmark schemes.

Energy minimization for IRS-and-UAV-assisted mobile edge computing

Intelligent reconfigurable surface (IRS) is an emerging technology for the enhancement of spectrum and energy efficiency. We propose a novel IRS-and-unmanned aerial vehicle (UAV)-Assisted mobile edge computing (MEC) framework, where a MEC server installing on an UAV to facilitate task calculations by mobile users (MUs), and an IRS modulates channels between MUs and the UAV. Non-orthogonal multiple access (NOMA) is employed for further improving system-wide spectral efficiency. There are needs for joint optimization of multiple parameters, e.g., the task partition parameters and the transmit power of all MUs, the reflection coefficient matrix of the IRS and the movement trajectory of the UAV, and such needs raises the challenge of minimizing the long-term total energy consumption of all MUs while satisfying required transmission rate and task completion delay. We divide optimization tasks into two sub-problems and propose specific solutions respectively, i.e., relevant decisions about the UAV and MUs to be solved by deep reinforcement learning (DRL); and the reflection coefficient matrix of the IRS to be solved by block coordinate descent (BCD). A series of experiments have verified the effectiveness of the proposed communication techniques and optimization algorithms. Simulation results demonstrate that (1) NOMA-IRS technique achieves better energy efficacy compared to the cases where random IRS or no IRS is deployed and the conventional orthogonal multiple access (OMA) technique with IRS. (2) our proposed deep deterministic policy gradient (DDPG)-BCD algorithm outperforms other four benchmark algorithms in solving the complex and dynamic optimization problem.

Efficient method for symmetric nonnegative matrix factorization with an approximate augmented Lagrangian scheme

In this paper, we propose an efficient method for solving symmetric nonnegative matrix factorization following an approximate augmented Lagrangian scheme. The augmented Lagrangian subproblem was solved column by column under the block coordinate descent (BCD) framework. In particular, we extend the recursive formula for rank-k nonnegative least squares problems by Chu et al. (2021) to subproblems generated by BCD framework in our method. Thereafter we derive the closed-form solution for k=4. Experiments for clustering show that the proposed method is noticeably efficient and achieves competitive performance compared with state-of-the-art methods.

Structured neural networks for CPUE standardization: A case study of the blue endeavour prawn in Australia's Northern Prawn Fishery

We performed a study on standardizing the catch per unit effort (CPUE) for blue endeavour prawns (Metapenaeus endeavouri) caught in the Northern Prawn Fishery (NPF), one of Australia’s largest and most valuable prawn fisheries. Blue endeavour prawns constitute a significant proportion of the total NPF catches. However, there have been very limited studies on their population dynamics. This study assessed the effectiveness of Artificial Neural Networks (ANNs) for CPUE standardization, with a focus on blue endeavour prawns as a case study. Our approach involved developing new ANN models for CPUE standardization with two key ideas: using an architecture inspired by the catch equation to mitigate overfitting; and using the Tweedie distribution to manage uncertainties and zero counts in the catch data. Specifically, we grouped variables into three distinct modules based on the catch equation, with each representing catchability, fishing effort, and fish density, respectively. Parameter estimation for our ANNs was achieved by maximizing the likelihood using a coordinate descent approach, which alternates between optimizing the Tweedie distribution parameters (power and dispersion) and the standard neural net parameters. We conducted a comprehensive comparison among ANNs, generalized linear models, and generalized additive models. The findings suggest that customizing ANN structure improves model fitting and effectively mitigates the risk of overfitting. It also reveals a promising path for the application of neural networks in CPUE standardization.

Tensor-based statistical learning methods for diagnosing product quality defects in multistage manufacturing processes

Multistage manufacturing processes with identical stages provide three-dimensional process data in which the first dimension represents the process (control/sensing) variable, the second is the stage, and the third is the measurement/sampling/data acquisition time point. Diagnosing quality faults in such processes often requires the simultaneous identification of crucial process variables and stages associated with product quality anomalies. Most existing diagnosis methods convert 3D data into a 2D matrix, resulting in loss of information and reduced diagnostic accuracy and stability. To address this challenge, we propose a penalized tensor regression model that regresses the product quality index against its 3D process data. For the estimation of high-dimensional regression coefficients with the limited amount of historical data, we apply the CANDECOMP/PARAFAC and Tucker decompositions to the coefficient tensor, which significantly reduces the number of parameters to be estimated. Based on the decompositions, a new regularization term is designed to enable the joint identification of critical process variables and stages. To estimate the parameters, we develop the block coordinate proximal descent algorithm and provide its convergence guarantee. Numerical studies demonstrate that the proposed methods can enhance diagnostic stability and on average improve the diagnostic accuracy by around 20% over existing benchmarks.

ORBIT SELECTION OF THE SPACE INDUSTRIAL PLATFORM WITH DISTRIBUTED ELECTRICAL-POWER SYSTEM MODULES

Space industrialization is one of the prospective directions in modern aerospace science and engineering for space exploration of new resources and habitats. The key issue is to provide industrial space modules with the required amount of electricity needed. One type of power supply for such modules is the use of distributed power systems, which consist of constellations of spacecraft with contactless power transmission. Given this, the problem of rational orbit selection for their dislocation arises. Considering these problems, the methodology for orbits selection of the space industrial platform with distributed electrical-power system modules is proposed in the paper. This methodology includes orbital translation, attitude, relative dynamics estimation for each power satellite, and its corresponding orbit optimization algorithm. The orbit optimization algorithm includes statistical processing and elements of gradient and coordinate descent methods, allowing us to determine the most significant parameter influencing the duration of the contactless power transmission session. Also, quaternion mathematics is used to estimate the dynamics in the program parameters for targeting the transmitter spacecraft antenna to the receiver spacecraft rectenna. With the approaches mentioned above, the methodology proposed in this paper allows us to form the requirements for the power satellites’ attitude and orbit control system to improve the process of selecting corresponding design parameters of such systems. Thus, the usage of the proposed methodology can allow the designing of the power satellites’ attitude and orbit control system in the conceptual stages of designing.

Energy efficiency optimization for 6G multi-IRS multi-cell NOMA vehicle-to-infrastructure communication networks

Intelligent Reflecting Surfaces (IRS), software-controlled metasurfaces, have emerged as an upcoming sixth-generation (6G) wireless communication technology. IRS intelligently manipulates and optimizes signal propagation using a large-scale array of intelligent elements, enhancing signal coverage, increasing capacity, mitigating path loss, and combating multipath fading This work provides a new energy-efficiency model for multi-IRS-assisted multi-cell non-orthogonal multiple access (NOMA) vehicular to infrastructure communication networks. The objective is the joint optimization of the total power budget at the roadside unit (RSU), NOMA power allocation for the user equipment, and designing phase shifts for IRS in each cell to maximize the achievable energy efficiency of the system. Due to non-convexity, the original non-convex problem is first decoupled and transformed using block coordinate descent and successive convex approximation methods. Then, an efficient solution is achieved using Gradient-based and interior-point methods. We also consider two benchmark schemes: (1) NOMA power optimization at RSU with random phase shift design at IRS and (2) orthogonal multiple access power allocation with optimal phase shift design at IRS. Numerical results show the superiority of the proposed solution compared to the benchmark schemes. The proposed solution outperforms the benchmarks, demonstrating a 59.57% and 151.21% improvement over the NOMA and orthogonal schemes, respectively, at pct=2 dBm. Additionally, it shows up to a 10.43% better performance than OMA at 10 IRS elements.

LPI Radar Sequence Design Against Cyclostationary Analysis

In this paper, we present a novel unimodular sequence design algorithm based on the coordinate descent (CD) algorithm, aimed at countering electronic surveillance (ES) systems based on cyclostationary analysis. Our algorithm not only provides resistance against cyclostationary analysis (CSA) but also maintains low integrated sidelobe (ISL) characteristics. Initially, we derive the expression of the cyclostationary feature (CSF) detector and simplify it into an iterative quadratic form. Additionally, we derive a quadratic form to ensure the similarity of the autocorrelation sidelobes. To balance the minimization of the detection probability and the ISL values, we introduce a Pareto scalar that transforms the multi-objective optimization problem into a convex combination of objective functions. This approach allows us to find an optimal trade-off between the two objectives. Finally, we propose a monotonic algorithm based on the CD algorithm to counter CSA analysis. This algorithm efficiently solves the optimization problem mentioned earlier. Numerical experiments are conducted to validate the correctness and effectiveness of our proposed algorithm.

Optimized ultrasound neuromodulation for non-invasive control of behavior and physiology

Focused ultrasound can non-invasively modulate neural activity, but whether effective stimulation parameters generalize across brain regions and cell types remains unknown. We used focused ultrasound coupled with fiber photometry to identify optimal neuromodulation parameters for four differentarousal centers of the brain in an effort to yield overt changes in behavior. Applying coordinate descent, we found that optimal parameters for excitation or inhibition are highly distinct, the effects of which are generally conserved across brain regions and cell types. Optimized stimulations induced clear,target-specific behavioral effects, whereas non-optimized protocols of equivalent energy resulted in substantially less or no change in behavior. These outcomes were independent of auditory confounds and, contrary to expectation, accompanied by a cyclooxygenase-dependent and prolonged reduction inlocal blood flow and temperature with brain-region-specific scaling. These findings demonstrate that carefully tuned and targeted ultrasound can exhibit powerful effects on complex behavior and physiology.

3D airborne electromagnetic data inversion based on the block coordinate descent method

Airborne electromagnetic (AEM) surveys usually cover a large area and create a large amount of data. This has limited the application of 3D AEM inversions. To make 3D AEM data inversion at a large scale possible, the local mesh method has been developed to avoid solving large matrix equations in 3D AEM modeling. However, the local mesh only saves the computational cost and memory during forward modeling and Jacobian calculations. When the survey area is very large, the cost for storing and solving the inversion equations can be very high. This brings significant challenges to practical 3D AEM inversions. To solve this problem, we develop a 3D scheme based on the block coordinate descent (BCD) method for inversions of large-scale AEM data. The BCD method divides the inversion for large models into series of small-local inversions, so that we can avoid solving the large matrix equations. Numerical experiments determine that the BCD method can obtain very similar results to those from the existing inversion methods but saves huge amounts of memory.

A Regularized Cox Hierarchical Model for Incorporating Annotation Information in Predictive Omic Studies.

Associated with high-dimensional omics data there are often "meta-features" such as biological pathways and functional annotations, summary statistics from similar studies that can be informative for predicting an outcome of interest. We introduce a regularized hierarchical framework for integrating meta-features, with the goal of improving prediction and feature selection performance with time-to-event outcomes. A hierarchical framework is deployed to incorporate meta-features. Regularization is applied to the omic features as well as the meta-features so that high-dimensional data can be handled at both levels. The proposed hierarchical Cox model can be efficiently fitted by a combination of iterative reweighted least squares and cyclic coordinate descent. In a simulation study we show that when the external meta-features are informative, the regularized hierarchical model can substantially improve prediction performance over standard regularized Cox regression. We illustrate the proposed model with applications to breast cancer and melanoma survival based on gene expression profiles, which show the improvement in prediction performance by applying meta-features, as well as the discovery of important omic feature sets with sparse regularization at meta-feature level. The proposed hierarchical regularized regression model enables integration of external meta-feature information directly into the modeling process for time-to-event outcomes, improves prediction performance when the external meta-feature data is informative. Importantly, when the external meta-features are uninformative, the prediction performance based on the regularized hierarchical model is on par with standard regularized Cox regression, indicating robustness of the framework. In addition to developing predictive signatures, the model can also be deployed in discovery applications where the main goal is to identify important features associated with the outcome rather than developing a predictive model.

Resource and trajectory optimization for UAV-assisted MEC communication systems over unlicensed spectrum band

The new radio unlicensed (NR-U) technology is proposed by 3GPP to extend NR to the unlicensed spectrum because of the shortage of the licensed spectrum. Different from the ground and fixed communication equipment-based unlicensed spectrum access scheme, the unmanned aerial vehicle (UAV) mobile platform-based unlicensed spectrum access scheme is not only related to incumbent users but also its trajectory and resource allocation. Therefore, this paper proposes a hybrid unlicensed spectrum access scheme for the UAV-assisted unlicensed mobile edge computing (MEC) communication (UAUM) system, where each flight time slot of the UAV is divided into two parts: power free (PF) and power controlled (PC) stages. In the PF stage, the transmit power is only restrained by the unlicensed spectrum regulations, and thus the UAV can provide high-rate services for real-time downlink users (RDUs) and uplink computing users (UCUs). In the PC stage, the transmit power of the UAV is mainly restrained by the interference to WiFi devices, and thus UAV can be allowed to provide low-rate services for non-realtime downlink users (NDUs) without affecting WiFi users. Based on the proposed scheme, a multi-variable optimization problem regarding trajectory, bandwidth, transmit power, and duty cycle is formulated to maximize the total offloaded computing bits on the premise of ensuring the quality of experience of RDUs, NDUs, and WiFi users under the maximum energy budget. To solve this problem efficiently, we propose an iterative algorithm based on the block coordinate descent method and successive convex approximation technique to decompose the original problem into four optimization subproblems of trajectory, bandwidth, transmit power and duty cycle, which are then solved alternatively in an iterative manner. A large number of simulation results demonstrate that in terms of spectrum efficiency and total offloaded computing bits, the proposed algorithm outperforms other unlicensed spectrum access schemes and optimization algorithms. The other performances of the proposed algorithm are deeply evaluated to prove its effectiveness and feasibility.

Nonlinear acoustic echo cancellation using low-complexity low-rank recursive least-squares algorithms

Adaptive exponential functional link networks (AEFLN) are a type of linear-in-the-parameter nonlinear filters, which have shown enhanced modeling capability for nonlinear systems. However, the convergence speed of traditional AEFLN is generally slow for long impulse responses, hence, AEFLN trained using recursive least-squares becomes an attractive choice to achieve faster convergence. Moreover, huge computational burden of RLS makes it unsuitable in practical applications like echo cancellation. While low complexity versions of RLS are widely available in literature, they still suffer from low convergence speed. To address this issue, we propose a nonlinear acoustic echo cancellation (NAEC) system using AEFLN-RLS, based on the nearest Kronecker product (NKP) decomposition and low-rank approximation technique, which not only reduces computational complexity but also achieves improved convergence speed (especially tracking). To further improve the echo cancellation performance in non-stationary conditions, a variable regularization approach based NKP-AEFLN-RLS system is also proposed. To also reduce the computational complexity further, dichotomous coordinate descent (DCD) updates are incorporated into the proposed NKP-AEFLN-RLS NAEC system and its variable regularization version. Experimental results show the effectiveness of the proposed algorithms, with the variable regularized version of the algorithm using DCD iterations showing the best compromise between convergence capability and lower computational complexity.

Vertex Block Descent

We introduce vertex block descent, a block coordinate descent solution for the variational form of implicit Euler through vertex-level Gauss-Seidel iterations. It operates with local vertex position updates that achieve reductions in global variational energy with maximized parallelism. This forms a physics solver that can achieve numerical convergence with unconditional stability and exceptional computation performance. It can also fit in a given computation budget by simply limiting the iteration count while maintaining its stability and superior convergence rate. We present and evaluate our method in the context of elastic body dynamics, providing details of all essential components and showing that it outperforms alternative techniques. In addition, we discuss and show examples of how our method can be used for other simulation systems, including particle-based simulations and rigid bodies.

Development and validation of a predictive model for PACU hypotension in elderly patients undergoing sedated gastrointestinal endoscopy

BackgroundHypotension, characterized by abnormally low blood pressure, is a frequently observed adverse event in sedated gastrointestinal endoscopy procedures. Although the examination time is typically short, hypotension during and after gastroscopy procedures is frequently overlooked or remains undetected. This study aimed to construct a risk nomogram for post-anesthesia care unit (PACU) hypotension in elderly patients undergoing sedated gastrointestinal endoscopy.MethodsThis study involved 2919 elderly patients who underwent sedated gastrointestinal endoscopy. A preoperative questionnaire was used to collect data on patient characteristics; intraoperative medication use and adverse events were also recorded. The primary objective of the study was to evaluate the risk of PACU hypotension in these patients. To achieve this, the least absolute shrinkage and selection operator (LASSO) regression analysis method was used to optimize variable selection, involving cyclic coordinate descent with tenfold cross-validation. Subsequently, multivariable logistic regression analysis was applied to build a predictive model using the selected predictors from the LASSO regression. A nomogram was visually developed based on these variables. To validate the model, a calibration plot, receiver operating characteristic (ROC) curve, and decision curve analysis (DCA) were used. Additionally, external validation was conducted to further assess the model’s performance.ResultsThe LASSO regression analysis identified predictors associated with an increased risk of adverse events during surgery: age, duration of preoperative water abstinence, intraoperative mean arterial pressure (MAP) <65 mmHg, decreased systolic blood pressure (SBP), and use of norepinephrine (NE). The constructed model based on these predictors demonstrated moderate predictive ability, with an area under the ROC curve of 0.710 in the training set and 0.778 in the validation set. The DCA indicated that the nomogram had clinical applicability when the risk threshold ranged between 20 and 82%, which was subsequently confirmed in the external validation with a range of 18–92%.ConclusionIncorporating factors such as age, duration of preoperative water abstinence, intraoperative MAP <65 mmHg, decreased SBP, and use of NE in the risk nomogram increased its usefulness for predicting PACU hypotension risk in elderly patient undergoing sedated gastrointestinal endoscopy.