This paper presents a 24-30 GHz sideband reuse transmitter with high image rejection ratio (IRR) and high local oscillator feedthrough (LOFT) suppression for 5G millimeter wave communication. Based on the Hartley heterodyne structure, the proposed sideband reuse scheme significantly reduces the required LO bandwidth for covering the 24–30 GHz RF output range. The LO bandwidth is narrowed to 2 GHz from the 6 GHz required in conventional heterodyne transmitters. As a result, excellent IRR and LOFT suppression are achieved across the operating band using a narrowband and simple-structure I/Q LO generation network. Moreover,$g_{\text {m}}$-boosting, linearity-enhanced mixer and power combining technique are employed in the transmitter to achieve high gain and output power. The proposed transmitter is fabricated in low-cost 180-nm bulk CMOS process. It delivers superior IRR greater than 37 dBc and LOFT below −41 dBc across the 24-30 GHz. The small signal 3-dB gain bandwidth spans from 24 to 30 GHz, with a peak gain of 21.7dB attained at 27.5 GHz. The complete transmitter achieves a measured saturated output power (Psat) of 16.5 dBm with 11.1% power-added efficiency (PAE) and the output 1-dB compression point (OP${}_{\mathbf {1dB}}$) of 14.8 dBm at 1.8V supply. Furthermore, with the 64-quadrature amplitude modulation (QAM) modulated signal, the proposed transmitter achieves an average output power of 8.7dBm at 27.5 GHz with the adjacent channel power ratio (ACPR) of −32.7 dBc.

Curriculum learning has emerged as an effective strategy to enhance the training efficiency and generalization of machine learning models. However, its theoretical underpinnings remain relatively underexplored. In this work, we develop a theoretical framework for curriculum learning based on biased regularized empirical risk minimization (RERM), identifying conditions under which curriculum learning provably improves generalization. We introduce a sufficient condition that characterizes a "good" curriculum and analyze a multi-task curriculum framework, where solving a sequence of convex tasks can facilitate better generalization. We also demonstrate how these theoretical insights translate to practical benefits when using stochastic gradient descent (SGD) as an optimization method. Beyond convex settings, we explore the utility of curriculum learning for non-convex tasks. Empirical evaluations on synthetic datasets and MNIST validate our theoretical findings and highlight the practical efficacy of curriculum-based training.

Intelligent systems have been widely used in various fields. They generate a large number of high‐dimensional time series monitoring data in the process of operation, which often hide various potential abnormal conditions, which bring hidden dangers to the stable operation of the system. Existing anomaly detection methods mainly focus on the sequence characteristics of time series data, but often ignore the correlation between different variables of multivariate data, and the detection efficiency is low when facing high‐dimensional time series data. To solve the above problems, we propose a deep anomaly detection method based on graph neural network, and combined with the big data computing framework Apache Flink, we construct a real‐time anomaly detection system for large‐scale high‐dimensional time series data. Experimental results on SWaT and WADI show that our proposed method can accurately detect anomalies in multivariate time series data, and can perform low‐latency real‐time anomaly detection on high‐dimensional industrial streaming data.

Community search in heterogeneous graphs is fundamental to applications such as expert team formation and scholarly collaboration. Many existing studies leverage meta-paths, which are sequences of node and edge types, to capture semantic relationships in heterogeneous graphs. However, most of them only consider the existence of meta-path instances, overlooking their frequency and thus failing to capture relationship strength. This limitation can result in communities that include nodes with numerous but weak relations. To capture the strength of relationships in heterogeneous graphs, we define the Strong Community (StrCom) model, which evaluates the strength between users based on the number of connecting meta-path instances. Building upon this model, we further propose the Budgeted Strong Community (BSC) problem by incorporating a size constraint. We provide theoretical analyses showing that the BSC problem is NP-hard and not in APX. To address this problem, we design three strategies-Shrink, Expand, and Hybrid-along with several optimization techniques to improve efficiency. Extensive experiments on large real-world datasets (e.g., DBLP, YAGO, DBpedia) demonstrate the effectiveness and efficiency of our approach. Specifically, our method achieves 3.49-107.09× higher PathSim scores for StrCom and two to five orders of magnitude higher scores for BSC compared to state-of-the-art baselines, demonstrating that the identified communities are both semantically coherent and structurally compact.

Benign overfitting is the phenomenon wherein none of the predictors in the hypothesis class can achieve perfect accuracy (i.e., non-realizable or noisy setting), but a model that interpolates the training data still achieves good generalization. A series of recent works aim to understand this phenomenon for regression and classification tasks using linear predictors as well as two-layer neural networks. In this paper, we study such a benign overfitting phenomenon in an adversarial setting. We show that under a distributional assumption, interpolating neural networks found using adversarial training generalize well despite inference-time attacks. Specifically, we provide convergence and generalization guarantees for adversarial training of two-layer networks (with smooth as well as non-smooth activation functions) showing that under moderate $\ell_2$ norm perturbation budget, the trained model has near-zero robust training loss and near-optimal robust generalization error. We support our theoretical findings with an empirical study on synthetic and real-world data.

Adversarial training has emerged as a popular approach for training models that are robust to inference-time adversarial attacks. However, our theoretical understanding of why and when it works remains limited. Prior work has offered generalization analysis of adversarial training, but they are either restricted to the Neural Tangent Kernel (NTK) regime or they make restrictive assumptions about data such as (noisy) linear separability or robust realizability. In this work, we study the stability and generalization of adversarial training for two-layer networks **without any data distribution assumptions** and **beyond the NTK regime**. Our findings suggest that for networks with *any given initialization* and *sufficiently large width*, the generalization bound can be effectively controlled via early stopping. We further improve the generalization bound by leveraging smoothing using Moreau’s envelope.

With the virtual synchronous generator (VSG) technology gradually becoming an emerging technology for new energy consumption, its introduction has solved the problems of weak support and weak anti-interference of traditional new energy stations. However, the practice shows that the grid-connected characteristics of VSG limit its large-scale utilization, and there is little research on the interaction between VSG and a multi-machine system. In this paper, small signal models and time domain simulation models of each link of a photovoltaic(PV) power station with the PV virtual synchronous generator (PV-VSG) are first conducted, and then the influence of the grid-connected PV power station with the PV-VSG on the low-frequency oscillation of power system and its interaction mechanism with the multi-machine system are qualitatively obtained based on the small signal analysis method and prony analysis method from two dimensions of frequency domain and time domain, respectively. The analysis and simulation show that the PV power station based on VSG technology affects the dynamic characteristics of the system by changing the electromagnetic torque of each synchronous generator. Unreasonable operating conditions and parameter settings will aggravate the phenomenon of low-frequency oscillation of the system. Before the grid connection of PV power station, the operating parameters shall be reasonably set to ensure their safe and stable grid connection.

Sliced Stein discrepancy (SSD) and its kernelized variants have demonstrated promising successes in goodness-of-fit tests and model learning in high dimensions. Despite the theoretical elegance, their empirical performance depends crucially on the search of the optimal slicing directions to discriminate between two distributions. Unfortunately, previous gradient-based optimisation approach returns sub-optimal results for the slicing directions: it is computationally expensive, sensitive to initialization, and it lacks theoretical guarantee for convergence. We address these issues in two steps. First, we show in theory that the requirement of using optimal slicing directions in the kernelized version of SSD can be relaxed, validating the resulting discrepancy with finite random slicing directions. Second, given that good slicing directions are crucial for practical performance, we propose a fast algorithm for finding good slicing directions based on ideas of active sub-space construction and spectral decomposition. Experiments in goodness-of-fit tests and model learning show that our approach achieves both the best performance and the fastest convergence. Especially, we demonstrate 14-80x speed-up in goodness-of-fit tests when compared with the gradient-based approach.

Paraphrase generation plays key roles in NLP tasks such as question answering, machine translation, and information retrieval. In this paper, we propose a novel framework for paraphrase generation. It simultaneously decodes the output sentence using a pretrained wordset-to-sequence model and a round-trip translation model. We evaluate this framework on Quora, WikiAnswers, MSCOCO and Twitter, and show its advantage over previous state-of-the-art unsupervised methods and distantly-supervised methods by significant margins on all datasets. For Quora and WikiAnswers, our framework even performs better than some strongly supervised methods with domain adaptation. Further, we show that the generated paraphrases can be used to augment the training data for machine translation to achieve substantial improvements.

Summary Visual interaction is one of the most important ways for mobile robots to serve the elderly in the future. Mobile robots need to recognize human movements to follow human movements or evade actions. An indoor mobile robot interaction system based on cloud servers is presented. In a human‐machine coexistence environment, the mobile robot recognizes human motion, which represents the control intention for robot. In addition, if the person does not issue a control command, the robot follows the operator moving trajectory as a follower. A mobile robot with four Mecanum wheels is used in experiments. In the robot, a 3D camera is used to capture human motion and recognizes the language control commands. Then, the mobile robot executes the command action after translating the human body language to its motion direction control mode. Moreover, a 2D camera in the robot is used to autonomously capture 2D human multi‐view images and combines facial recognition to achieve specific human target to follow‐up. Some experiments are presented to verify the effectiveness of the whole Interaction control system.

To improve the performance of EAs on large scale numerical optimization problems, a number of techniques have been invented, among which, Cooperative Coevolution (CC in short) is obviously a promising one. But sometimes CC is easy to lead to premature convergence in large scale global optimization. In this paper, a Cooperative Coevolution Evolutionary Algorithm (CCEA in short) with global search (CCGS) is presented to handle large scale global optimization (LSGO) problems. The performance of CCGS is evaluated on the test functions provided for the CEC 2012 competition and special session on Large Scale Global Optimization. The experiment results show that this technique is more effective than CCEAs without global search.

Cooperative Coevolutionary Evolutionary Algorithm is an extension of conventional Evolutionary Algorithm: it implements the idea of divide and conquer by dividing the whole set of variables into several subsets (groups), and evolve each subset independently with a certain optimizer. How to group the variables effectively have been studied by several researchers. Quite a number of variable grouping strategies have been proposed, in most of which, the correlation among variables is considered as the most important factor for guiding grouping, although its legitimacy has not been investigated comprehensively. In this paper an empirical analysis is conducted to testify the legitimacy of assumption that the correlation among variables is an important factor for variable grouping. The experiment results show that, although in some situation, the performance of random grouping is better than that of grouping based on the correct correlation knowledge, the variable correlation is obviously an important factor affecting the performance of the grouping strategies.

During the last decade, a large number of evolutionary algorithmic variants have been proposed for diverse optimization tasks, most of which are practical engineering applications. In the previous research, one variant is always designed for one specific engineering application. In IEEE Congress on Evolutionary Competition, the numerical optimization competition is held to benchmark different optimization algorithms for more general applications. In this paper, we conduct the optimization method estimation of distribution and differential evolution (ED-DE) by implementing a two-stage ensemble idea, whose effectiveness and efficiency has been experimentally verified.