NeurIPS 2020poster4 citations
Variance reduction for Random Coordinate Descent-Langevin Monte Carlo
Abstract
Sampling from a log-concave distribution function is one core problem that has wide applications in Bayesian statistics and machine learning. While most gradient free methods have slow convergence rate, the Langevin Monte Carlo (LMC) that provides fast convergence requires the computation of gradients. In practice one uses finite-differencing approximations as surrogates, and the method is expensive in high-dimensions.
BibTeX
@inproceedings{NEURIPS2020_272e1170,
author = {DING, ZHIYAN and Li, Qin},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {3748--3760},
publisher = {Curran Associates, Inc.},
title = {Variance reduction for Random Coordinate Descent-Langevin Monte Carlo},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/272e11700558e27be60f7489d2d782e7-Paper.pdf},
volume = {33},
year = {2020}
}