We study stochastic monotone inclusion problems, which widely appear in machine learning applications, including robust regression and adversarial learning. We propose novel variants of stochastic Halpern iteration with recursive variance reduction. In the cocoercive -- and more generally Lipschitz-monotone -- setup, our algorithm attains $\epsilon$ norm of the operator with $\mathcal{O}(\frac{1}{\epsilon^3})$ stochastic operator evaluations, which significantly improves over state of the art $\mathcal{O}(\frac{1}{\epsilon^4})$ stochastic operator evaluations required for existing monotone inclusion solvers applied to the same problem classes. We further show how to couple one of the proposed variants of stochastic Halpern iteration with a scheduled restart scheme to solve stochastic monotone inclusion problems with ${\mathcal{O}}(\frac{\log(1/\epsilon)}{\epsilon^2})$ stochastic operator evaluations under additional sharpness or strong monotonicity assumptions.
翻译:我们研究的是在机器学习应用中广泛出现的单体内融合问题,包括强力回归和对抗性学习。我们提出了具有递归性差异减少作用的软体Halpern迭代的新型变体。在可凝固性 -- -- 更普遍的Lipschitz-mononoone -- -- 设置中,我们的算法达到了操作者以$\mathcal{O}(\frac{1-hunsilon}3})的操作者标准,用$\mathcal{O}(\frac_log_mathcal{O}(\\\\ epsilon4})(frac{1-unsilon_4}) 用于现有单体内融合溶剂溶液溶液溶剂所需的复变体性操作者评价在相同的类别中应用。我们进一步展示了如何将所拟议的可凝固性卤性二变体内循环体内操作者变体内的一种变体与一个预定的重新恢复计划,用$_mathal{O}(\\\\\\\\\\\\\\\\) pryst的操作者变体内再评价的硬性硬性假设下如何结合。