• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2013 Information Theory and Applications Workshop >Online learning and adaptation over networks: More information is not necessarily better
【24h】

Online learning and adaptation over networks: More information is not necessarily better

机译：网络上的在线学习和适应：更多信息不一定更好

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We examine the performance of stochastic-gradient learners over connected networks for global optimization problems involving risk functions that are not necessarily quadratic. We consider two well-studied classes of distributed schemes including consensus strategies and diffusion strategies. We quantify how the mean-square-error and the convergence rate of the network vary with the combination policy and with the fraction of informed agents. Several combination policies are considered including doubly-stochastic rules, the averaging rule, Metropolis rule, and the Hastings rule. It will be seen that the performance of the network does not necessarily improve with a larger proportion of informed agents. A strategy to counter the degradation in performance is presented.
机译：对于涉及风险函数（不一定是二次方）的全局优化问题，我们研究了连通网络上随机梯度学习器的性能。我们考虑两类经过仔细研究的分布式方案，包括共识策略和扩散策略。我们量化网络的均方误差和收敛速度如何随组合策略和知情代理的比例而变化。考虑了几种组合策略，包括双随机规则，平均规则，Metropolis规则和Hastings规则。将会看到，网络的性能并不一定会随着更大比例的知情代理而提高。提出了一种应对性能下降的策略。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号