Asynchronous stochastic Quasi-Newton MCMC for non-convex optimization supplementary document
Lists
Only you see this
Abstract
Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By building up on this recent theory, in this study, we develop an asynchronous-parallel stochastic L-BFGS algorithm for non-convex optimization. The proposed algorithm is suitable for both distributed and shared-memory settings. We provide formal theoretical analysis and show that the proposed method achieves an ergodic convergence rate of {equation Presented} (N being the total number of iterations) and it can achieve a linear speedup under certain conditions. We perform several experiments on both synthetic and real datasets. The results support our theory and show that the proposed algorithm provides a significant speedup over the recently proposed synchronous distributed L-BFGS algorithm.
BibTeX
@inproceedings{simsekli2018asynchronous,
author = {Umut Şimşekli and Çağatay Yıldız and Thanh Huy Nguyen and Gaël Richard and Ali Taylan Cemgil},
title = {{Asynchronous stochastic Quasi-Newton MCMC for non-convex optimization supplementary document}},
booktitle = {Aaltodoc},
year = {2018},
}