arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01945math.NAcs.LGcs.NA
收藏

多层Stein变分梯度下降及其在贝叶斯逆问题中的应用

Multilevel Stein variational gradient descent with applications to Bayesian inverse problems

Courant Institute of Mathematical Sciences, New York University(纽约大学库朗数学科学研究所)

Terrence Alsup, Luca Venturi, Benjamin Peherstorfer

摘要:

这项工作提出了一个多层次的变化斯坦变分梯度下降,更有效地从目标分布的样本。关键成分是一系列分布,其保真度和成本不断增加,并向目标利益分布收敛。例如,这样的分布序列是由贝叶斯逆问题中的正向模型的更精细离散化水平的层次结构给出的。所提出的多级Stein变分梯度下降将大部分迭代移动到较低,较便宜的水平,目的是与仅使用最高级别分布的传统单级Stein变分梯度下降变体相比,仅需要在较高,较昂贵的水平上进行少量迭代。在一定的假设下,在平均场的限制,所提出的多级Stein方法的误差衰减的对数因子比单级对应的计算成本方面的错误。贝叶斯反问题的数值实验表明,加速比一个以上的数量级的建议多层次的斯坦方法相比,单级的变体,只使用最高级别。

英文摘要:

This work presents a multilevel variant of Stein variational gradient descent to more efficiently sample from target distributions. The key ingredient is a sequence of distributions with growing fidelity and costs that converges to the target distribution of interest. For example, such a sequence of distributions is given by a hierarchy of ever finer discretization levels of the forward model in Bayesian inverse problems. The proposed multilevel Stein variational gradient descent moves most of the iterations to lower, cheaper levels with the aim of requiring only a few iterations on the higher, more expensive levels when compared to the traditional, single-level Stein variational gradient descent variant that uses the highest-level distribution only. Under certain assumptions, in the mean-field limit, the error of the proposed multilevel Stein method decays by a log factor faster than the error of the single-level counterpart with respect to computational costs. Numerical experiments with Bayesian inverse problems show speedups of more than one order of magnitude of the proposed multilevel Stein method compared to the single-level variant that uses the highest level only.

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。

↑