arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.07072math.OCcs.CVcs.NAmath.NA
收藏

通过非凸majorization-minimization进行复合优化

Composite Optimization by Nonconvex Majorization-Minimization

University of Siegen(明斯特大学)

Jonas Geiping, Michael Moeller

AI总结:

本文提出非凸majorization-minimization方法用于非凸复合函数优化,证明其能实现全局收敛,并通过实验展示其在深度超分辨率中的优越性。

摘要:

非凸复合函数的最小化可以建模多种成像任务。解决此类问题的流行算法是majorization-minimization技术,通过迭代用易于最小化的majorizing函数近似复合非凸函数。大多数技术,例如梯度下降,利用凸majorizers以保证majorizer易于最小化。在我们的工作中,我们考虑了一类自然的非凸majorizers,并证明这些majorizers仍然足以实现全局收敛的优化方案。数值结果表明,当非凸majorizers被求解到全局最优时,通过应用此方案,可以经常获得比以前的majorization-minimization方法更好的局部最优解。最后,我们展示了我们的算法在从原始时间飞行数据中进行深度超分辨率中的行为。

英文摘要:

The minimization of a nonconvex composite function can model a variety of imaging tasks. A popular class of algorithms for solving such problems are majorization-minimization techniques which iteratively approximate the composite nonconvex function by a majorizing function that is easy to minimize. Most techniques, e.g. gradient descent, utilize convex majorizers in order to guarantee that the majorizer is easy to minimize. In our work we consider a natural class of nonconvex majorizers for these functions, and show that these majorizers are still sufficient for a globally convergent optimization scheme. Numerical results illustrate that by applying this scheme, one can often obtain superior local optima compared to previous majorization-minimization methods, when the nonconvex majorizers are solved to global optimality. Finally, we illustrate the behavior of our algorithm for depth super-resolution from raw time-of-flight data.

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。

↑