Accelerating Level-Value Adjustment for the Polyak Stepsize
arxiv(2023)
摘要
The Polyak stepsize formula has been widely used for subgradient methods for
convex optimization. However, calculating the stepsize requires the optimal
objective value, which is generally unknown. Dynamic estimations of the optimal
objective value are thus usually needed. In this paper, to guarantee
convergence, a series of level values is constructed to successively estimate
the optimal objective value. This is achieved by developing a decision-based
procedure through a novel easy-to-solve ``Polyak Stepsize Violation Detector''
(PSVD) linear constraint satisfaction problem. Once a violation is detected,
the level value is recalculated. We rigorously establish convergence for level
and objective values. Through a series of empirical tests of convex functions
with diverse characteristics, we illustrate the practical advantages of our
approach as compared to existing methods.
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