arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.02511math.OC
收藏

具有自适应步长的随机原始-对偶混合梯度算法

Stochastic Primal Dual Hybrid Gradient Algorithm with Adaptive Step-Sizes

Antonin Chambolle, Claire Delplancke, Matthias J. Ehrhardt, Carola-Bibiane Schönlieb, Junqi Tang

AI总结:

本文针对SPDHG算法步长选择缺乏系统方法的问题,提出一类自适应SPDHG算法并证明其收敛性,同时给出满足理论假设的参数更新策略,通过CT成像数值实验验证了其有效性。

摘要:

在本文中,我们提出了一种新的具有自适应步长的原始-对偶算法。具有恒定步长的随机原始-对偶混合梯度(SPDHG)算法由于其可扩展性,已在许多科学领域的大规模凸优化中得到广泛应用。虽然原始步长和对偶步长的乘积受上界约束以确保收敛,但步长之比的选择在应用中至关重要。迄今为止,尚无系统且成功的方法来为SPDHG选择原始步长和对偶步长。在本文中,我们提出了一类通用的自适应SPDHG(A-SPDHG)算法,并在弱假设下证明了其收敛性。我们还提出了具体的参数更新策略,这些策略满足我们理论的假设,从而得到收敛算法。计算机断层成像上的数值例子证明了所提方案的有效性。

英文摘要:

In this work we propose a new primal-dual algorithm with adaptive step-sizes. The stochastic primal-dual hybrid gradient (SPDHG) algorithm with constant step-sizes has become widely applied in large-scale convex optimization across many scientific fields due to its scalability. While the product of the primal and dual step-sizes is subject to an upper-bound in order to ensure convergence, the selection of the ratio of the step-sizes is critical in applications. Up-to-now there is no systematic and successful way of selecting the primal and dual step-sizes for SPDHG. In this work, we propose a general class of adaptive SPDHG (A-SPDHG) algorithms, and prove their convergence under weak assumptions. We also propose concrete parameters-updating strategies which satisfy the assumptions of our theory and thereby lead to convergent algorithms. Numerical examples on computed tomography demonstrate the effectiveness of the proposed schemes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑