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 1708.02544cs.LGcs.AImath.OCstat.ML
收藏

Bandit抽样下的随机优化

Stochastic Optimization with Bandit Sampling

EPFL(洛桑联邦理工学院)

Farnood Salehi, L. Elisa Celis, Patrick Thiran

摘要:

许多随机优化算法通过从训练集中均匀随机地采样数据点来动态地估计成本函数的梯度。然而,估计器可能具有较大的方差,这无意中减慢了算法的收敛速度。减少这种差异的一种方法是从精心选择的非均匀分布中对数据点进行采样。在这项工作中,我们提出了一种新的非均匀采样方法,使用多臂强盗框架。理论上,我们表明,我们的算法渐近近似的最佳方差的一个因素内的3。经验上,我们表明,使用这种数据点选择技术的结果显着减少收敛时间和方差的几个随机优化算法,如SGD,SVRG和SAGA。这种采样数据点的方法是通用的,可以与任何使用无偏梯度估计的算法结合使用-我们希望它具有广泛的适用性,超出了本工作中探索的具体示例。

英文摘要:

Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently slows down the convergence rate of the algorithms. One way to reduce this variance is to sample the datapoints from a carefully selected non-uniform distribution. In this work, we propose a novel non-uniform sampling approach that uses the multi-armed bandit framework. Theoretically, we show that our algorithm asymptotically approximates the optimal variance within a factor of 3. Empirically, we show that using this datapoint-selection technique results in a significant reduction in the convergence time and variance of several stochastic optimization algorithms such as SGD, SVRG and SAGA. This approach for sampling datapoints is general, and can be used in conjunction with any algorithm that uses an unbiased gradient estimation -- we expect it to have broad applicability beyond the specific examples explored in this work.

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。

↑