Accelerating Frank-Wolfe via Averaging Step Directions

arxiv(2022)

引用 0|浏览1
暂无评分
摘要
The Frank-Wolfe method is a popular method in sparse constrained optimization, due to its fast per-iteration complexity. However, the tradeoff is that its worst case global convergence is comparatively slow, and importantly, is fundamentally slower than its flow rate--that is to say, the convergence rate is throttled by discretization error. In this work, we consider a modified Frank-Wolfe where the step direction is a simple weighted average of past oracle calls. This method requires very little memory and computational overhead, and provably decays this discretization error term. Numerically, we show that this method improves the convergence rate over several problems, especially after the sparse manifold has been detected. Theoretically, we show the method has an overall global convergence rate of $O(1/k^p)$, where $0< p < 1$; after manifold identification, this rate speeds to $O(1/k^{3p/2})$. We also observe that the method achieves this accelerated rate from a very early stage, suggesting a promising mode of acceleration for this family of methods.
更多
查看译文
关键词
step directions,frank-wolfe
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