arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1704.04752math.STstat.TH
收藏

采样和optimization之间更进一步更强的类比:朗之万蒙特卡罗和梯度下降

Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent

Arnak S. Dalalyan

摘要:

在本文中,我们重新审视最近建立的理论保证的Langevin Monte Carlo算法的采样从光滑和(强)对数凹密度的收敛性。我们改进了现有的结果时,收敛测量Wasserstein距离,并提供进一步的见解非常紧密的关系,一方面,朗之万蒙特卡罗采样,另一方面,梯度下降优化。最后,我们还建立了一个版本的朗之万蒙特卡罗算法,是基于噪声的梯度评估的收敛性保证。

英文摘要:

In this paper, we revisit the recently established theoretical guarantees for the convergence of the Langevin Monte Carlo algorithm of sampling from a smooth and (strongly) log-concave density. We improve the existing results when the convergence is measured in the Wasserstein distance and provide further insights on the very tight relations between, on the one hand, the Langevin Monte Carlo for sampling and, on the other hand, the gradient descent for optimization. Finally, we also establish guarantees for the convergence of a version of the Langevin Monte Carlo algorithm that is based on noisy evaluations of the gradient.

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。

↑