Popular repositories Loading
-
-
-
-
-
-
SigmaX_OCP
SigmaX_OCP Public采用梯度法作为基本方法。在启发式步长的基础上,采用简单准则与后退方法、Armijo-Goldstein准则、Wolfe-Powell准则作为确保梯度下降的步长搜索准则。采用自适应梯度、均方根传播、经典动量、自适应矩估计作为历史累计的方向优化方案来处理鞍点。同时包含罚函数法、KKT条件和同伦延拓等内容
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.