咨询与建议

限定检索结果

文献类型

  • 3 篇 期刊文献

馆藏范围

  • 3 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 计算机科学与技术...
    • 1 篇 控制科学与工程
  • 1 篇 理学
    • 1 篇 数学
  • 1 篇 医学
    • 1 篇 基础医学(可授医学...
    • 1 篇 临床医学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 3 篇 non-smooth non-c...
  • 1 篇 neural nets
  • 1 篇 subgradient-orie...
  • 1 篇 bilinear matrix ...
  • 1 篇 linear matrix in...
  • 1 篇 static output fe...
  • 1 篇 strict model
  • 1 篇 stochastic algor...
  • 1 篇 non-gradient ite...
  • 1 篇 convex optimizat...
  • 1 篇 structured stati...
  • 1 篇 upper- and lower...
  • 1 篇 kurdyka-lojasiew...
  • 1 篇 robustness

机构

  • 1 篇 univ manchester ...
  • 1 篇 univ florida dep...
  • 1 篇 linkoping univ d...
  • 1 篇 univ toulouse 3 ...
  • 1 篇 univ toulouse cn...

作者

  • 1 篇 peaucelle dimitr...
  • 1 篇 sadabadi mandieh...
  • 1 篇 noll dominikus
  • 1 篇 mukherjee anirbi...
  • 1 篇 karmakar sayar

语言

  • 3 篇 英文
检索条件"主题词=Non-smooth non-convex optimization"
3 条 记 录,以下是1-10 订阅
排序:
Provable training of a ReLU gate with an iterative non-gradient algorithm
收藏 引用
NEURAL NETWORKS 2022年 第0期151卷 264-275页
作者: Karmakar, Sayar Mukherjee, Anirbit Univ Florida Dept Stat 230 Newell Dr Gainesville FL 32611 USA Univ Manchester Dept Comp Sci Kilburn Bldg Manchester M13 9PL Lancs England
In this work, we demonstrate provable guarantees on the training of a single ReLU gate in hitherto unexplored regimes. We give a simple iterative stochastic algorithm that can train a ReLU gate in the realizable setti... 详细信息
来源: 评论
From static output feedback to structured robust static output feedback: A survey
收藏 引用
ANNUAL REVIEWS IN CONTROL 2016年 42卷 11-26页
作者: Sadabadi, Mandieh S. Peaucelle, Dimitri Linkoping Univ Dept Elect Engn Div Automat Control Linkoping Sweden Univ Toulouse CNRS LAAS Toulouse France
This paper reviews the vast literature on static output feedback design for linear time-invariant systems including classical results and recent developments. In particular, we focus on static output feedback synthesi... 详细信息
来源: 评论
Convergence of non-smooth Descent Methods Using the Kurdyka-Aojasiewicz Inequality
收藏 引用
JOURNAL OF optimization THEORY AND APPLICATIONS 2014年 第2期160卷 553-572页
作者: Noll, Dominikus Univ Toulouse 3 Inst Math F-31062 Toulouse France
We investigate the convergence of subgradient-oriented descent methods in non-smooth non-convex optimization. We prove convergence in the sense of subsequences for functions with a strict standard model, and we show t... 详细信息
来源: 评论