Stochastic gradient Hamiltonian Monte Carlo with variance reduction for Bayesian inference

• Main Authors: LI, Zhize, ZHANG, Tianyi, CHENG, Shuyu, ZHU, Jun, LI, Jian
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2019
• Subjects: Hamiltonian Monte Carlo; Variance reduction; Bayesian inference; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8689; https://ink.library.smu.edu.sg/context/sis_research/article/9692/viewcontent/ML19_vrhmc.pdf
• Institution: Singapore Management University

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stochastic gradients evaluated on mini-batches are used as a replacement. In order to...