arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.08998cs.LGeess.SPstat.ML
收藏

扩散归一化最小均值M-估计算法研究

Study of Diffusion Normalized Least Mean M-estimate Algorithms

Southwest University of Science and Technology(西南科技大学);PUC-Rio(里约热内卢天主教大学);University of York(约克大学)

Y. Yu, H. He, T. Yang, X. Wang, R. C. de Lamare

摘要:

提出了一种基于修正Huber函数的扩散归一化最小均值M估计算法,该算法能够使分布式网络在脉冲干扰下具有鲁棒的学习能力。为了利用系统的基本稀疏性,以进一步提高学习性能,稀疏意识的变体也开发了通过将$l_0$ -范数的估计到更新过程中。然后,我们分析了瞬态,稳态和稳定性行为的算法在一个统一的框架。特别是,我们提出了一种分析方法,比传统的方法来处理得分函数,因为它删除了积分和价格定理的要求。在各种脉冲噪声环境下的仿真结果表明,所提出的算法优于现有的一些扩散算法,理论结果是可验证的。

英文摘要:

This work proposes diffusion normalized least mean M-estimate algorithm based on the modified Huber function, which can equip distributed networks with robust learning capability in the presence of impulsive interference. In order to exploit the system's underlying sparsity to further improve the learning performance, a sparse-aware variant is also developed by incorporating the $l_0$-norm of the estimates into the update process. We then analyze the transient, steady-state and stability behaviors of the algorithms in a unified framework. In particular, we present an analytical method that is simpler than conventional approaches to deal with the score function since it removes the requirements of integrals and Price's theorem. Simulations in various impulsive noise scenarios show that the proposed algorithms are superior to some existing diffusion algorithms and the theoretical results are verifiable.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑