arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.13413cs.LGstat.ML
收藏

基于二分搜索和一阶梯度的随机优化方法

Binary Search and First Order Gradient Based Method for Stochastic Optimization

Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校)

Vijay Pandey

摘要:

在本文中,我们提出了一种新的随机优化方法,它使用二进制搜索技术与一阶梯度为基础的优化方法,称为二进制搜索梯度优化(BSG)或BiGrad。在这种优化设置中,非凸曲面被视为一组凸曲面。在BSG中,首先定义一个区域,假设区域是凸的。如果区域不是凸的,则算法很快离开该区域并定义一个新的区域,否则,算法试图收敛于该区域的最优点。在BSG中,二叉搜索的核心目的是确定区域在对数时间内是否是凸的,而基于一阶梯度的方法主要用于定义新的区域。在本文中,Adam被用作基于一阶梯度的方法,然而,也可以考虑这类的其他方法。在深度神经网络设置中,它有效地处理了梯度消失和爆炸的问题。我们使用逻辑回归和深度神经网络在MNIST手写数字、IMDB和CIFAR10数据集上评估BSG。与其他基于一阶梯度的优化方法相比,我们产生了更有前途的结果。此外,与其他方法相比,该算法在看不见的数据上具有更好的泛化能力。

英文摘要:

In this paper, we present a novel stochastic optimization method, which uses the binary search technique with first order gradient based optimization method, called Binary Search Gradient Optimization (BSG) or BiGrad. In this optimization setup, a non-convex surface is treated as a set of convex surfaces. In BSG, at first, a region is defined, assuming region is convex. If region is not convex, then the algorithm leaves the region very fast and defines a new one, otherwise, it tries to converge at the optimal point of the region. In BSG, core purpose of binary search is to decide, whether region is convex or not in logarithmic time, whereas, first order gradient based method is primarily applied, to define a new region. In this paper, Adam is used as a first order gradient based method, nevertheless, other methods of this class may also be considered. In deep neural network setup, it handles the problem of vanishing and exploding gradient efficiently. We evaluate BSG on the MNIST handwritten digit, IMDB, and CIFAR10 data set, using logistic regression and deep neural networks. We produce more promising results as compared to other first order gradient based optimization methods. Furthermore, proposed algorithm generalizes significantly better on unseen data as compared to other methods.

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。

↑