In this paper, we study the adversarial robustness of deep neural networks (DNN) for classification against optimal classifiers. We look at the smallest magnitude of possible additive perturbations that can change a classifier's output. We provide a matrix-theoretic explanation of the adversarial fragility of DNNs for classification. In particular, our theoretical results show that the adversarial robustness of a neural network can degrade as the input dimension d increases. Analytically, we show that the adversarial robustness of neural networks can be only 1/√d of the best possible adversarial robustness of optimal classifiers. Our theories match remarkably well with empirical results. The matrix-theoretic explanation aligns with an earlier information-theoretic feature-compression-based explanation for the adversarial fragility of neural networks.

Gamification has been effectively applied in organizational and academic training to enhance motivation. Among various game elements, leaderboards are particularly popular in gamified training environments. Grounded in gamification research, self-determination theory, and job demands-resources theory, this research investigates the relationships among leaderboard affordance, perceived role importance in a team (PRIT), satisfaction of the three psychological needs (perceived autonomy, competence, and relatedness), and two types of stress (distress and eustress). Using a team-based ERP simulation game for gamified ERP training, we conducted two studies (Study 1: N = 203 and Study 2: N = 216) and employed structural equation modelling to test our hypotheses. Our findings indicate that leaderboard affordance positively influences PRIT. Additionally, the results show that leaderboard affordance and PRIT increase needs satisfaction and eustress, while the effects on distress were minimal. This study contributes to gamification IS research by highlighting the impact of leaderboard affordances and PRIT in fostering positive psychological outcomes and expanding our understanding of stress in gamified training contexts. Our findings are important for organizations seeking to maintain motivation and engagement through gamified training.

This paper delves into the subject of designing a tree network, enabling the application of Distributed Dual Coordinate Ascent on a general tree network (DDCA-Tree) introduced in [1] – [3] for distributed Machine Learning (ML) process. We assume that a network is characterized by communication delays proportional to the distance between any two nodes. To efficiently managing distributed data across the network, we propose the Minimum Worst-Distance Tree (MWDT) algorithm for designing a tree network with a specified target depth yielding a network structure where the communication delay in worst path between a leaf node and its parent node is minimized, consequently enhancing the convergence speed of DDCA-Tree. In numerical experiments, to validate the effectiveness of our approach, we compared the communication delay in worst path on a tree network generated by our algorithm against a minimum spanning tree which provides minimum weight (i.e., distance) sum, and showed our network design has reduced distance in worst path.

The rapid spread of SARS-CoV-2 has placed a significant burden on public health systems to provide swift and accurate diagnostic testing highlighting the critical need for innovative testing approaches for future pandemics. In this study, we present a novel sample pooling procedure based on compressed sensing theory to accurately identify virally infected patients at high prevalence rates utilizing an innovative viral RNA extraction process to minimize sample dilution. At prevalence rates ranging from 0-14.3%, the number of tests required to identify the infection status of all patients was reduced by 69.26% as compared to conventional testing in primary human SARS-CoV-2 nasopharyngeal swabs and a coronavirus model system. Our method provided quantification of individual sample viral load within a pool as well as a binary positive-negative result. Additionally, our modified pooling and RNA extraction process minimized sample dilution which remained constant as pool sizes increased. Compressed sensing can be adapted to a wide variety of diagnostic testing applications to increase throughput for routine laboratory testing as well as a means to increase testing capacity to combat future pandemics.

Due to the big size of data and limited data storage volume of a single computer or a single server, data are often stored in a distributed manner. Thus, performing large-scale machine learning operations with the distributed datasets through communication networks is often required. In this paper, we study the convergence rate of the distributed dual coordinate ascent for distributed machine learning problems in a general tree-structured network. Since a tree network model can be understood as the generalization of a star network, our algorithm can be thought of as the generalization of the distributed dual coordinate ascent in a star network. We provide the convergence rate of the distributed dual coordinate ascent over a general tree network in a recursive manner and analyze the network effect on the convergence rate. Secondly, by considering network communication delays, we optimize the distributed dual coordinate ascent algorithm to maximize its convergence speed. From our analytical result, we can choose the optimal number of local iterations depending on the communication delay severity to achieve the fastest convergence speed. In numerical experiments, we consider machine learning scenarios over communication networks, where local workers cannot directly reach to a central node due to constraints in communication, and demonstrate that the usability of our distributed dual coordinate ascent algorithm in tree networks.

In this paper, we propose and evaluate a new communication-efficient design technique for solving the linear quadratic regulator (LQR) optimal control problem. We propose this design to minimize the communication overhead and resulting energy consumption in wireless distributed control scenarios in the context of cooperative vehicular networking (CVN). We introduce the LQR optimal control design problem, then we propose our new design technique using the alternating direction method of multipliers (ADMM). Our numerical results demonstrate that our communication-efficient control design can outperform the previous methods namely the sparsity-promoting optimal control design and the conventional LQR optimal control design. We also provide simulation results to evaluate the resilience of proposed technique under various wireless connectivity conditions.

Subspace tracking is an important problem in signal processing that finds applications in wireless communications, video surveillance, and source localization in radar and sonar. In recent years, it is recognized that a low-dimensional subspace can be estimated and tracked reliably even when the data vectors are partially observed with many missing entries, which is greatly desirable when processing high-dimensional and high-rate data to reduce the sampling requirement. This paper is motivated by the observation that the underlying low-dimensional subspace may possess additional structural properties induced by the physical model of data, which if harnessed properly, can greatly improve subspace tracking performance. As a case study, this paper investigates the problem of tracking direction-of-arrivals from subsampled observations in a unitary linear array, where the signals lie in a subspace spanned by columns of a Vandermonde matrix. We exploit the shift-invariant structure by mapping the data vector to a latent Hankel matrix, and then perform tracking over the Hankel matrices by exploiting their low-rank properties. Numerical simulations are conducted to validate the superiority of the proposed approach over existing subspace tracking methods that do not exploit the additional shift-invariant structure in terms of tracking speed and agility.

With explosion of data size and limited storage space at a single location, data are often distributed at different locations. We thus face the challenge of performing large-scale machine learning from these distributed data through communication networks. In this paper, we generalize the distributed dual coordinate ascent in a star network to a general tree structured network, and provide the convergence rate analysis of the general distributed dual coordinate ascent. In numerical experiments, we demonstrate that the performance of the distributed dual coordinate ascent in a tree network can outperform that of the distributed dual coordinate ascent in a star network when a network has a lot of communication delays between the center node and its direct child nodes.

We consider the problem of recovering the superposition of R distinct complex exponential functions from compressed non-uniform time-domain samples. Total Variation (TV) minimization or atomic norm minimization was proposed in the literature to recover the R frequencies or the missing data. However, in order for TV minimization and atomic norm minimization to recover the missing data or the frequencies, the underlying R frequencies are required to be well-separated, even when the measurements are noiseless. This paper shows that the Hankel matrix recovery approach can super-resolve the R complex exponentials and their frequencies from compressed nonuniform measurements, regardless of how close their frequencies are to each other. We propose a new concept of orthonormal atomic norm minimization (OANM), and demonstrate that the success of Hankel matrix recovery in separation-free super-resolution comes from the fact that the nuclear norm of a Hankel matrix is an orthonormal atomic norm. More specifically, we show that, in traditional atomic norm minimization, the underlying parameter values must be well separated to achieve successful signal recovery, if the atoms are changing continuously with respect to the continuously-valued parameter. In contrast, for the OANM, it is possible the OANM is successful even though the original atoms can be arbitrarily close.

Phaseless super-resolution refers to the problem of super-resolving a signal from only its low-frequency Fourier magnitude measurements. In this paper, we consider the phaseless super-resolution problem of recovering a sum of sparse Dirac delta functions which can be located anywhere in the continuous time-domain. For such signals in the continuous domain, we propose a novel Semidefinite Programming (SDP) based signal recovery method to achieve the phaseless super-resolution. This work extends the recent work of Jaganathan et al. [1], which considered phaseless super-resolution for discrete signals on the grid.

We propose fast algorithms that speed up or improve the performance of recovering spectrally sparse signals from un-derdetermined measurements. Our algorithms are based on a non-convex approach of using alternating projected gradient descent for structured matrix recovery. We apply this approach to two formulations of structured matrix recovery: Hankel and Toeplitz mosaic structured matrix, and Hankel structured matrix. Our methods provide better recovery performance, and faster signal recovery than existing algorithms, including atomic norm minimization.

We propose novel algorithms that enhance the performance of recovering unknown continuous-valued frequencies from undersampled signals. Our iterative reweighted frequency recovery algorithms employ the support knowledge gained from earlier steps of our algorithms as block prior information to enhance frequency recovery. Our methods improve the performance of the atomic norm minimization which is a useful heuristic in recovering continuous-valued frequency contents. Numerical results demonstrate that our block iterative reweighted methods provide both better recovery performance and faster speed than other known methods.

Recent research in off-the-grid compressed sensing (CS) has demonstrated that, under certain conditions, one can successfully recover a spectrally sparse signal from a few time-domain samples even though the dictionary is continuous. In this paper, we extend off-the-grid CS to applications where some prior information about spectrally sparse signal is known. We specifically consider cases where a few contributing frequencies or poles, but not their amplitudes or phases, are known a priori. Our results show that equipping off-the-grid CS with the known-poles algorithm can increase the probability of recovering all the frequency components.

In this paper, we consider robust system identification under sparse outliers and random noises. In our problem, system parameters are observed through a Toeplitz matrix. All observations are subject to random noises and a few are corrupted with outliers. We reduce this problem of system identification to a sparse error correcting problem using a Toeplitz structured real-numbered codingmatrix. We prove the performance guarantee of Toeplitz structured matrix in sparse error correction. Thresholds on the percentage of correctable errors for Toeplitz structured matrices are also established. When both outliers and observation noise are present, we have shown that the estimation error goes to 0 asymptotically as long as the probability density function for observation noise is not “vanishing” around 0.