In this paper, we propose a novel solution for non-convex problems of multiple variables, especially for those typically solved by an alternating minimization (AM) strategy that splits the original optimization problem into a set of sub-problems corresponding to each variable, and then iteratively optimize each sub-problem using a fixed updating rule. However, due to the intrinsic non-convexity of the original optimization problem, the optimization can usually be trapped into spurious local minimum even when each sub-problem can be optimally solved at each iteration. Meanwhile, learning-based approaches, such as deep unfolding algorithms, are highly limited by the lack of labelled data and restricted explainability. To tackle these issues, we propose a meta-learning based alternating minimization (MLAM) method, which aims to minimize a partial of the global losses over iterations instead of carrying minimization on each sub-problem, and it tends to learn an adaptive strategy to replace the handcrafted counterpart resulting in advance on superior performance. Meanwhile, the proposed MLAM still maintains the original algorithmic principle, which contributes to a better interpretability. We evaluate the proposed method on two representative problems, namely, bi-linear inverse problem: matrix completion, and non-linear problem: Gaussian mixture models. The experimental results validate that our proposed approach outperforms AM-based methods in standard settings, and is able to achieve effective optimization in challenging cases while other comparing methods would typically fail.
翻译:在本文中,我们提出了一个解决多种变量的非混凝土问题的新解决方案,特别是对于通常通过交替最小化(AM)战略解决的多变量的非混混问题,这种战略将原始优化问题分为与每个变量相对应的一组子问题,然后利用固定更新规则迭代优化每个子问题。然而,由于原始优化问题的内在非混混杂性,优化通常会被困在虚假的本地最低标准中,即使每个次级问题都可以在每次循环中最佳地解决。与此同时,学习方法,如深层演算法,由于缺乏标签数据和解释有限而高度限制。为了解决这些问题,我们建议采用基于交替最小化(MLAM)方法的元学习,目的是尽量减少全球在迭代上损失的一部分,而不是将每个子问题最小化,而且往往学习适应性战略,以取代在每次迭代最佳业绩中出现的手巧的对应方。同时,拟议的司法协助机制仍然维持原始的算法原则,例如深演算法,因为缺乏标签数据和解释性有限的解释性。为了解决这些问题,我们建议采用基于交替最小化的最小化的最小化方法,我们提出的标准化方法,在两种方法中,即:在两个模型中,我们提出的双级化方法,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,我们提出的方法上,在结构上,在结构上,在结构上,在结构上,在结构上,在结构上,我们提出的是比较问题上,在两种方法是比较问题,在两种方法,在两个上,我们提出的方法,在两种方法,在结构上,在两种方法上,在两种方法上,即:在结构上,我们提出的方法上,在结构上,在结构上,我们提出的方法上,在结构上,在结构上,在结构上,在方法上,在两个方法上,在方法上,在结构上,在结构上,在结构上,在方法上,在方法上,在方法上,在方法上,在两个上,在比较方法上,在方法上,在方法上,在方法是,在方法上,在方法上,在两个方法上,在方法上,在两个方法上,在两个方法上,在比较方法上,在比较上,在