论文标题
加速随机顺序二次编程，用于使用预测差异降低的相等性优化的优化
Accelerating Stochastic Sequential Quadratic Programming for Equality Constrained Optimization using Predictive Variance Reduction
论文作者
论文摘要
在本文中，我们提出了一种随机方法来解决利用预测差异的相等约束优化问题。具体而言，我们基于采用梯度近似值差异的顺序二次编程范式开发一种方法。在合理的假设下，我们证明，在我们所提出的算法产生的迭代元素中评估的一阶平稳性度量衡量，从任意起点和适应性步长策略中都收敛到零。最后，我们证明了我们提出的算法对机器学习中出现的受约束二进制分类问题的实际性能。
In this paper, we propose a stochastic method for solving equality constrained optimization problems that utilizes predictive variance reduction. Specifically, we develop a method based on the sequential quadratic programming paradigm that employs variance reduction in the gradient approximations. Under reasonable assumptions, we prove that a measure of first-order stationarity evaluated at the iterates generated by our proposed algorithm converges to zero in expectation from arbitrary starting points, for both constant and adaptive step size strategies. Finally, we demonstrate the practical performance of our proposed algorithm on constrained binary classification problems that arise in machine learning.
