arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07070math.OC
收藏

最小值和优化问题的高效算法

Efficient Algorithms for Sum-of-Minimum Optimization

Lisang Ding, Ziang Chen, Xinshang Wang, Wotao Yin

AI总结:

本文提出“最小值和”优化模型,并受 k-means 初始化与 Lloyd 算法启发设计高效求解算法,给出初始化紧界和类梯度下降收敛速率,在多个任务上验证了其优越性。

摘要:

在这项工作中,我们提出了一种新的优化模型,称为“最小值和”优化。该模型旨在对 $N$ 个目标函数在 $k$ 个参数上的和或平均值进行最小化,其中每个目标函数取一个预定义子函数关于这 $k$ 个参数的最小值。这一通用框架涵盖了机器学习及相关领域中的众多聚类应用。受经典 $k$-means 的随机初始化算法(Arthur & Vassilvitskii, 2007)和 Lloyd 算法(Lloyd, 1982)的启发,我们开发了用于求解最小值和优化问题的高效算法。我们为广义初始化算法建立了一个新的紧界,并证明了广义 Lloyd 算法具有类似梯度下降的收敛速率。我们在多个任务上对所提算法的效率进行了数值检验,包括广义主成分分析、混合线性回归和小规模神经网络训练。与以往基于更简单但精度较低的优化重构方法相比,我们的方法表现更优。

英文摘要:

In this work, we propose a novel optimization model termed "sum-of-minimum" optimization. This model seeks to minimize the sum or average of $N$ objective functions over $k$ parameters, where each objective takes the minimum value of a predefined sub-function with respect to the $k$ parameters. This universal framework encompasses numerous clustering applications in machine learning and related fields. We develop efficient algorithms for solving sum-of-minimum optimization problems, inspired by a randomized initialization algorithm for the classic $k$-means (Arthur & Vassilvitskii, 2007) and Lloyd's algorithm (Lloyd, 1982). We establish a new tight bound for the generalized initialization algorithm and prove a gradient-descent-like convergence rate for generalized Lloyd's algorithm. The efficiency of our algorithms is numerically examined on multiple tasks, including generalized principal component analysis, mixed linear regression, and small-scale neural network training. Our approach compares favorably to previous ones based on simpler-but-less-precise optimization reformulations.

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。

↑