arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0802.4382math.OC
收藏

R^d和希尔伯特空间中一类梯度算法的渐近性

Asymptotic behaviour of a family of gradient algorithms in R^d and Hilbert spaces

Luc Pronzato, Henry P. Wynn, Anatoly A. Zhigljavsky

摘要:

在R^d和希尔伯特空间中,分析了一类优化有界二次算子的梯度算法(包括最速下降法和最小留数法)的渐近性态.所得结果在几个方面推广了Akaike(1959)的结果。首先,在家庭中的所有算法被证明具有相同的渐近行为(收敛到两点吸引子),这意味着特别是他们有类似的渐近收敛率。其次,分析也涵盖了希尔伯特空间的情况。详细分析了吸引子的稳定性。

英文摘要:

The asymptotic behaviour of a family of gradient algorithms (including the methods of steepest descent and minimum residues) for the optimisation of bounded quadratic operators in R^d and Hilbert spaces is analyzed. The results obtained generalize those of Akaike (1959) in several directions. First, all algorithms in the family are shown to have the same asymptotic behaviour (convergence to a two-point attractor), which implies in particular that they have similar asymptotic convergence rates. Second, the analysis also covers the Hilbert space case. A detailed analysis of the stability property of the attractor is provided.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑