arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.07079math.OCcs.LG
收藏

基于主坐标下降的大规模快速离散最优化

Fast Large-Scale Discrete Optimization Based on Principal Coordinate Descent

Huan Xiong, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao

摘要:

二进制优化是离散最优化的一个代表性子类,在数学优化中起着重要作用,在计算机视觉和机器学习中有着广泛的应用。通常,二元最优化问题是NP-难的,由于二元约束的存在而难以求解,特别是当变量数目很大时。现有的方法通常具有高计算成本或大的累积量化误差,或者仅针对特定任务而设计。本文提出了一种求一般二元最优化问题有效近似解的快速算法。该算法迭代求解与损失函数的线性替代项相关的最小化问题,这导致在每一步中更新一些对损失函数的值影响最大的二元变量。我们的方法支持广泛的一类经验目标函数的$1$和$-1$的二进制变量的数量有/没有限制。此外,我们的算法的理论收敛性进行了证明,并推导出显式的收敛速度,目标函数的Lipschitz连续梯度,这是在实践中常用的。在多个二进制优化任务和大规模数据集上进行的大量实验表明,该算法在有效性和效率方面优于现有的几种方法。

英文摘要:

Binary optimization, a representative subclass of discrete optimization, plays an important role in mathematical optimization and has various applications in computer vision and machine learning. Usually, binary optimization problems are NP-hard and difficult to solve due to the binary constraints, especially when the number of variables is very large. Existing methods often suffer from high computational costs or large accumulated quantization errors, or are only designed for specific tasks. In this paper, we propose a fast algorithm to find effective approximate solutions for general binary optimization problems. The proposed algorithm iteratively solves minimization problems related to the linear surrogates of loss functions, which leads to the updating of some binary variables most impacting the value of loss functions in each step. Our method supports a wide class of empirical objective functions with/without restrictions on the numbers of $1$s and $-1$s in the binary variables. Furthermore, the theoretical convergence of our algorithm is proven, and the explicit convergence rates are derived, for objective functions with Lipschitz continuous gradients, which are commonly adopted in practice. Extensive experiments on several binary optimization tasks and large-scale datasets demonstrate the superiority of the proposed algorithm over several state-of-the-art methods in terms of both effectiveness and efficiency.

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。

↑