亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

In this paper, we consider a decentralized learning problem in the presence of stragglers. Although gradient coding techniques have been developed for distributed learning to evade stragglers, where the devices send encoded gradients with redundant training data, it is difficult to apply those techniques directly to decentralized learning scenarios. To deal with this problem, we propose a new gossip-based decentralized learning method with gradient coding (GOCO). In the proposed method, to avoid the negative impact of stragglers, the parameter vectors are updated locally using encoded gradients based on the framework of stochastic gradient coding and then averaged in a gossip-based manner. We analyze the convergence performance of GOCO for strongly convex loss functions. And we also provide simulation results to demonstrate the superiority of the proposed method in terms of learning performance compared with the baseline methods.

In this paper, we perform a non-asymptotic analysis of the federated linear stochastic approximation (FedLSA) algorithm. We explicitly quantify the bias introduced by local training with heterogeneous agents, and investigate the sample complexity of the algorithm. We show that the communication complexity of FedLSA scales polynomially with the desired precision $\epsilon$, which limits the benefits of federation. To overcome this, we propose SCAFFLSA, a novel variant of FedLSA, that uses control variates to correct the bias of local training, and prove its convergence without assumptions on statistical heterogeneity. We apply the proposed methodology to federated temporal difference learning with linear function approximation, and analyze the corresponding complexity improvements.

In this study, we consider the reliability assessment of anomaly detection (AD) using Variational Autoencoder (VAE). Over the last decade, VAE-based AD has been actively studied in various perspective, from method development to applied research. However, when the results of ADs are used in high-stakes decision-making, such as in medical diagnosis, it is necessary to ensure the reliability of the detected anomalies. In this study, we propose the VAE-AD Test as a method for quantifying the statistical reliability of VAE-based AD within the framework of statistical testing. Using the VAE-AD Test, the reliability of the anomaly regions detected by a VAE can be quantified in the form of p-values. This means that if an anomaly is declared when the p-value is below a certain threshold, it is possible to control the probability of false detection to a desired level. Since the VAE-AD Test is constructed based on a new statistical inference framework called selective inference, its validity is theoretically guaranteed in finite samples. To demonstrate the validity and effectiveness of the proposed VAE-AD Test, numerical experiments on artificial data and applications to brain image analysis are conducted.

We perform an error analysis of a fully discretised Streamline Upwind Petrov Galerkin Dynamical Low Rank (SUPG-DLR) method for random time-dependent advection-dominated problems. The time integration scheme has a splitting-like nature, allowing for potentially efficient computations of the factors characterising the discretised random field. The method allows to efficiently compute a low-rank approximation of the true solution, while naturally "inbuilding" the SUPG stabilisation. Standard error rates in the L2 and SUPG-norms are recovered. Numerical experiments validate the predicted rates.

In this paper, the sensing beam pattern gain under simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS)-enabled integrated sensing and communications (ISAC) systems is investigated, in which multiple targets and multiple users exist. However, multiple targets detection introduces new challenges, since the STAR-RIS cannot directly send sensing beams and detect targets, the dual-functional base station (DFBS) is required to analyze the echoes of the targets. While the echoes reflected by different targets through STAR-RIS come from the same direction for the DFBS, making it impossible to distinguish them. To address the issue, we first introduce the signature sequence (SS) modulation scheme to the ISAC system, and thus, the DFBS can detect different targets by the SS-modulated sensing beams. Next, via the joint beamforming design of DFBS and STAR-RIS, we develop a maxmin sensing beam pattern gain problem, and meanwhile, considering the communication quality requirements, the interference limitations of other targets and users, the passive nature constraint of STAR-RIS, and the total transmit power limitation. Then, to tackle the complex non-convex problem, we propose an alternating optimization method to divide it into two quadratic semidefinite program subproblems and decouple the coupled variables. Drawing on mathematical transformation, semidefinite programming, as well as semidefinite relaxation techniques, these two subproblems are iteratively sloved until convergence, and the ultimate solutions are obtained. Finally, simulation results are conducted to validate the benefits and efficiency of our proposed scheme.

This paper aims to analyze errors in the implementation of the Physics-Informed Neural Network (PINN) for solving the Allen--Cahn (AC) and Cahn--Hilliard (CH) partial differential equations (PDEs). The accuracy of PINN is still challenged when dealing with strongly non-linear and higher-order time-varying PDEs. To address this issue, we introduce a stable and bounded self-adaptive weighting scheme known as Residuals-RAE, which ensures fair training and effectively captures the solution. By incorporating this new training loss function, we conduct numerical experiments on 1D and 2D AC and CH systems to validate our theoretical findings. Our theoretical analysis demonstrates that feedforward neural networks with two hidden layers and tanh activation function effectively bound the PINN approximation errors for the solution field, temporal derivative, and nonlinear term of the AC and CH equations by the training loss and number of collocation points.

In this paper, we propose a continuous-time lidar-inertial odometry (CT-LIO) system named SLICT2, which promotes two main insights. One, contrary to conventional wisdom, CT-LIO algorithm can be optimized by linear solvers in only a few iterations, which is more efficient than commonly used nonlinear solvers. Two, CT-LIO benefits more from the correct association than the number of iterations. Based on these ideas, we implement our method with a customized solver where the feature association process is performed immediately after each incremental step, and the solution can converge within a few iterations. Our implementation can achieve real-time performance with a high density of control points while yielding competitive performance in highly dynamical motion scenarios. We demonstrate the advantages of our method by comparing with other existing state-of-the-art CT-LIO methods. The source code will be released for the benefit of the community.

The most famous error-decoding algorithm for convolutional codes is the Viterbi algorithm. In this paper, we present a new reduced complexity version of this algorithm which can be applied to a class of binary convolutional codes with optimum column distances called k-partial simplex convolutional codes.

In this paper, we introduce a novel Distributed Markov Chain Monte Carlo (MCMC) inference method for the Bayesian Non-Parametric Latent Block Model (DisNPLBM), employing the Master/Worker architecture. Our non-parametric co-clustering algorithm divides observations and features into partitions using latent multivariate Gaussian block distributions. The workload on rows is evenly distributed among workers, who exclusively communicate with the master and not among themselves. DisNPLBM demonstrates its impact on cluster labeling accuracy and execution times through experimental results. Moreover, we present a real-use case applying our approach to co-cluster gene expression data. The code source is publicly available at //github.com/redakhoufache/Distributed-NPLBM.

In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.