In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning. In the first-order case, we propose a framework of transition from deterministic or semi-deterministic to stochastic quadratic regularization methods. We leverage the two-phase nature of stochastic optimization to propose a novel first-order algorithm with adaptive sampling and adaptive step size. In the second-order case, we propose a novel stochastic damped L-BFGS method that improves on previous algorithms in the highly nonconvex context of deep learning. Both algorithms are evaluated on well-known deep learning datasets and exhibit promising performance.
翻译:在本文中,我们既考虑一阶和二阶技术,以解决在机器学习中产生的连续优化问题。在一阶情况下,我们提出了一个从确定或半确定性过渡到随机二次规范化方法的框架。我们利用随机优化的两阶段性质来提出具有适应性抽样和适应性步骤大小的新颖的一级算法。在第二阶情况下,我们提出了一个新型的随机立体式L-BFGS方法,该方法改进了在高度非对立的深层次学习背景下以前的算法。这两种算法都是根据众所周知的深层学习数据集进行评估的,并表现出有希望的表现。