研究Hilbert空间中一类不可微最优化问题的增量次梯度方法.证明了:当问题有解时,这种方法生成的点列是弱收敛于最优解的;当问题无解时,点列是无界的.同时给出了一个收敛速率的结果.
We consider an incremental subgradient method for minimizing a sum of nondifferentiable convex functions in a Hilbert space. We prove that the sequence generated by this method is weakly convergent to a minimizer if the problem has solutions, and is unbounded otherwise. We present also a convergence rate result.