Sufficient Conditions for Instability of the Subgradient Method with Constant Step Size
研究了常步长次梯度方法在局部Lipschitz半代数函数局部最小值附近不稳定的充分条件，这些条件适用于鲁棒主成分分析和神经网络中的虚假局部最小值。
We provide sufficient conditions for instability of the subgradient method with constant step size around a local minimum of a locally Lipschitz semialgebraic function. They are satisfied by several spurious local minima arising in robust principal component analysis and neural networks.<br>