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 2209.05045math.OCcs.CCcs.LG
收藏

确定和随机非光滑非凸Optimization的无约束方法

Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization

University of California, Berkeley(加州大学伯克利分校)

Tianyi Lin, Zeyu Zheng, Michael I. Jordan

摘要:

非光滑非凸最优化问题广泛存在于机器学习和商业决策中,而两个核心挑战阻碍了具有有限时间收敛保证的有效解方法的发展:缺乏计算上易于处理的最优性准则和缺乏计算上强大的预言机。本文的贡献是双重的。首先,我们建立了著名的Goldstein次微分~ \citep{Goldstein-1977-Optimization}与一致光滑化之间的关系,从而为设计保证有限时间收敛于Goldstein平稳点集的无梯度方法提供了依据和直观.其次,我们提出了求解一类非光滑非凸最优化问题的无梯度方法(GFM)和随机GFM,并证明了这两种方法都能在$O(d^{3/2}δ^{-1}ε^{-4})$以期望的收敛速度返回Lipschitz函数$f$的$(δ,ε)$ -Goldstein驻点,其中$d$是问题维数.还提出了GFM和SGFM的两个阶段版本,并证明可以实现改进的大偏差结果。最后,我们用\textsc{Minst}数据集证明了2-SGFM训练ReLU神经网络的有效性。

英文摘要:

Nonsmooth nonconvex optimization problems broadly emerge in machine learning and business decision making, whereas two core challenges impede the development of efficient solution methods with finite-time convergence guarantee: the lack of computationally tractable optimality criterion and the lack of computationally powerful oracles. The contributions of this paper are two-fold. First, we establish the relationship between the celebrated Goldstein subdifferential~\citep{Goldstein-1977-Optimization} and uniform smoothing, thereby providing the basis and intuition for the design of gradient-free methods that guarantee the finite-time convergence to a set of Goldstein stationary points. Second, we propose the gradient-free method (GFM) and stochastic GFM for solving a class of nonsmooth nonconvex optimization problems and prove that both of them can return a $(δ,ε)$-Goldstein stationary point of a Lipschitz function $f$ at an expected convergence rate at $O(d^{3/2}δ^{-1}ε^{-4})$ where $d$ is the problem dimension. Two-phase versions of GFM and SGFM are also proposed and proven to achieve improved large-deviation results. Finally, we demonstrate the effectiveness of 2-SGFM on training ReLU neural networks with the \textsc{Minst} dataset.

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。

↑