Underwater communication is widely regarded as one of the most significant challenges due to the unique physical properties of water. Among the available communication methods, radiofrequency communication offers high...
详细信息
Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, federated learning...
详细信息
ISBN:
(纸本)9781577358800
Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variancereduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples O(is an element of(-3)) and O(is an element of(-2)) communication rounds to find an is an element of-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.
Most of the existing distributed adaptive filtering algorithms over wireless sensor networks (WSNs) are developed, aiming to solve unconstrained network optimization problems. However, in practice, the weight coeffici...
详细信息
Most of the existing distributed adaptive filtering algorithms over wireless sensor networks (WSNs) are developed, aiming to solve unconstrained network optimization problems. However, in practice, the weight coefficients of the filter may need to satisfy a set of linear equations. Thus, a distributed adaptive algorithm that can solve the sensor network optimization problem under constraints is needed. Considering the possible impulsive interference in the observed signals, a novel robust distributed constrained adaptive algorithm called diffusion constrained least mean M-estimate (D-CLMM) is proposed by using the modified Huber function (MHF), which endows the network robustness to impulsive noise. The transient, steady-state performances and stability of the proposed D-CLMM are studied with the aid of some commonly used assumptions and verified by computer simulations. Moreover, the effectiveness of D-CLMM is verified in distributed parameter estimation and beamforming applications in non-Gaussian noise environments.
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledge for smart systems. However, the concept of machine unlearning has emerged as a tr...
详细信息
The aging of the global population makes the age-friendly design a hot topic in the design field and society. A three-dimensional indoor elderly friendly design system based on adaptive genetic algorithm is proposed t...
详细信息
In this paper, we introduce a versatile data-driven approach for servo-controlling the highly deformable robotic endoscope equipped with Draw Tower Gratings (DTGs). The advancement of perception and decision-making te...
详细信息
Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely studied, learning with heavy-tailed di...
详细信息
The safe operation of substation equipment will directly affect the power supply reliability of the substation. To guarantee the stability of the substation, a monitoring approach utilizing the BP neural network for a...
详细信息
In multivehicle autonomous systems that operate under unknown or adversarial environments, it is a challenging task to simultaneously achieve source seeking and obstacle avoidance. Indeed, even for single-vehicle syst...
详细信息
In multivehicle autonomous systems that operate under unknown or adversarial environments, it is a challenging task to simultaneously achieve source seeking and obstacle avoidance. Indeed, even for single-vehicle systems, smooth time-invariant feedback controllers based on navigation or barrier functions have been shown to be highly susceptible to arbitrarily small jamming signals that can induce instability in the closed-loop system, or that are able to stabilize spurious equilibria in the operational space. When the location of the source is further unknown, adaptive smooth source seeking dynamics based on averaging theory may suffer from similar limitations. In this article, we address this problem by introducing a class of novel distributed hybrid model-free controllers, that achieve robust source seeking and obstacle avoidance in multivehicle autonomous systems, with vehicles characterized by nonlinear continuous-time dynamics stabilizable by hybrid feedback. The hybrid source seeking law switches between a family of cooperative gradient-free controllers, derived from potential fields that satisfy mild invexity assumptions. The stability and robustness properties of the closed-loop system are analyzed using Lyapunov tools and singular perturbation theory for set-valued hybrid dynamical systems. The theoretical results are validated via numerical and experimental tests.
A signal processing method combining adaptive Singular Spectrum Decomposition (SSD) with Transient Extracting Transform (TET) is proposed to address the challenge of weak energy in early rolling bearing fault signals,...
详细信息
暂无评论