Mirror Langevin Monte Carlo: the Case Under Isoperimetry
Mirror Langevin Monte Carlo: the Case Under Isoperimetry
复制标题
Mirror Langevin Monte Carlo:等周法下的案例
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Qijia Jiang
中科院分区:
文献类型:
--
作者:
Qijia Jiang
Motivated by the connection between sampling and optimization, we study a mirror descent analogue of Langevin dynamics and analyze three different discretization schemes, giving nonasymptotic convergence rate under functional inequalities such as Log-Sobolev in the corresponding metric. Compared to the Euclidean setting, the result reveals intricate relationship between the underlying geometry and the target distribution and suggests that care might need to be taken in order for the discretized algorithm to achieve vanishing bias with diminishing stepsize for sampling from potentials under weaker smoothness/convexity regularity conditions.
DOI:
--
发表时间:
2022
期刊:
Algorithmic Learning Theory
影响因子:
--
作者:
Ruilin Li;Molei Tao;Santosh Vempala;Andre Wibisono
通讯作者:
Andre Wibisono
DOI:
--
发表时间:
2020-05
期刊:
ArXiv
影响因子:
--
作者:
Sinho Chewi;Thibaut Le Gouic;Chen Lu;Tyler Maunu;P. Rigollet;Austin J. Stromme
通讯作者:
Sinho Chewi;Thibaut Le Gouic;Chen Lu;Tyler Maunu;P. Rigollet;Austin J. Stromme
DOI:
--
发表时间:
2019-08
期刊:
ArXiv
影响因子:
--
作者:
Wenlong Mou;Yian Ma;Yi-An Ma;M. Wainwright;P. Bartlett;Michael I. Jordan
通讯作者:
Wenlong Mou;Yian Ma;Yi-An Ma;M. Wainwright;P. Bartlett;Michael I. Jordan