Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6594969 | Computers & Chemical Engineering | 2018 | 31 Pages |
Abstract
Benchmark tests result in a 20Ã-60Ã speedup but 14% increase in memory usage against emcee, a similar MCMC package in Python. Several MCMC hyperparameters were analyzed: number of temperatures, ensemble size, step size, and swap attempt frequency. Heuristic tuning guidelines are provided for setting these hyperparameters.
Keywords
Related Topics
Physical Sciences and Engineering
Chemical Engineering
Chemical Engineering (General)
Authors
Li Ang Zhang, Alisa Urbano, Gilles Clermont, David Swigon, Ipsita Banerjee, Robert S. Parker,