Implementation of Bregman--Moreau Unadjusted Mirror Langevin Algorithm (BMUMLA) in Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes (Lau and Liu, 2022), published at ICML 2022.
notebook/sampling_anisotropic_Laplace_bmumla.ipynb: sampling from an anisotropic Laplace distribution
notebook/sampling_bayesian_logistic_reg.ipynb: sampling from the posterior distribution of a Bayesian logistic regression model
notebook/sampling_uniform.ipynb: sampling from an anisotropic uniform distribution
The fig folder contains plots produced from the code appearing in the paper.
Tim Tsz-Kit Lau and Han Liu (2022). Bregman Proximal Langevin Monte Carlo via Bregman–Moreau Envelopes. In Proceedings of the 39th International Conference on Machine Learning (ICML). [abs] [pdf] [arXiv] [slides]