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 1105.4549math.OCcs.SYeess.SY
收藏

关于自适应步长序列的随机梯度和次梯度方法

On Stochastic Gradient and Subgradient Methods with Adaptive Steplength Sequences

University of Illinois(伊利诺伊大学)

Farzad Yousefian, Angelia Nedić, Uday V. Shanbhag

AI总结:

本文提出两种自适应步长方案用于强凸可微随机优化,并针对不可微目标提出局部平滑技术,使自适应步长框架适用于次梯度情形,实验表明方案性能良好且对用户定义参数依赖显著降低。

摘要:

标准随机逼近实现的性能可能因步长序列的选择而有显著差异,且通常缺乏关于良好选择的指导。基于这一差距,在论文的第一部分,我们提出了两种适用于强凸可微随机优化问题的自适应步长方案,并配备了收敛理论。第一种方案称为递归步长随机逼近方案,它优化误差界以导出一个规则,该规则将给定迭代处的步长表示为前一次迭代步长和某些问题参数的简单函数。该规则被认为在预设的选择集合上导出了最优步长序列。第二种方案称为级联步长随机逼近方案,它将步长序列保持为分段常数递减函数,当满足合适的误差阈值时步长减小。在论文的第二部分,我们允许不可微目标,并提出了一种局部平滑技术,该技术导致函数的可微近似。假设局部随机性服从均匀分布,我们建立了近似梯度的Lipschitz性质,并证明所获得的Lipschitz界随问题规模以适中的速率增长。这促进了自适应步长随机逼近框架的发展,该框架现在需要在原始测度和人为引入分布的乘积空间中进行采样。所得的自适应步长方案应用于三个随机优化问题。我们观察到两种方案在实践中表现良好,并且对用户定义参数的依赖显著降低。

英文摘要:

The performance of standard stochastic approximation implementations can vary significantly based on the choice of the steplength sequence, and in general, little guidance is provided about good choices. Motivated by this gap, in the first part of the paper, we present two adaptive steplength schemes for strongly convex differentiable stochastic optimization problems, equipped with convergence theory. The first scheme, referred to as a recursive steplength stochastic approximation scheme, optimizes the error bounds to derive a rule that expresses the steplength at a given iteration as a simple function of the steplength at the previous iteration and certain problem parameters. This rule is seen to lead to the optimal steplength sequence over a prescribed set of choices. The second scheme, termed as a cascading steplength stochastic approximation scheme, maintains the steplength sequence as a piecewise-constant decreasing function with the reduction in the steplength occurring when a suitable error threshold is met. In the second part of the paper, we allow for nondifferentiable objective and we propose a local smoothing technique that leads to a differentiable approximation of the function. Assuming a uniform distribution on the local randomness, we establish a Lipschitzian property for the gradient of the approximation and prove that the obtained Lipschitz bound grows at a modest rate with problem size. This facilitates the development of an adaptive steplength stochastic approximation framework, which now requires sampling in the product space of the original measure and the artificially introduced distribution. The resulting adaptive steplength schemes are applied to three stochastic optimization problems. We observe that both schemes perform well in practice and display markedly less reliance on user-defined parameters.

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。

↑