Performance estimation of stochastic first order methods
user-5f8cfb314c775ec6fa691ca8(2019)
摘要
We present an extension to the performance estimation methodology, allowing for a computer-assisted analysis of stochastic first-order methods. The approach is applicable in the convex and non-convex settings, and for various suboptimality criteria including the standard minimal gradient norm of the iterates. We describe the approach, new numerical and analytical bounds on the stochastic gradient method, and a construction of a worst-case example establishing tightness of the analyses.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要