具有最坏情况迭代复杂度O(ε^{-3/2})的非凸优化信赖域算法

A trust region algorithm with a worst-case iteration complexity of $$\mathcal{O}(\epsilon ^{-3/2})$$ O ( ε - 3 / 2 ) for nonconvex optimization

Mathematical Programming · 2016

被引 168 · 同刊同年前 4%