论文信息 - Stochastic Gradient MCMC with Repulsive Forces

Stochastic Gradient MCMC with Repulsive Forces

We propose a unifying view of two different families of Bayesian inference algorithms, SG-MCMC and SVGD. We show that SVGD plus a noise term can be framed as a multiple chain SG-MCMC method. Instead of treating each parallel chain independently from others, the proposed algorithm implements a repulsive force between particles, avoiding collapse. Experiments in both synthetic distributions and real datasets show the benefits of the proposed scheme.

David Ríos Insua | Víctor Gallego | D. Insua | Víctor Gallego

[1] Tianqi Chen,et al. A Complete Recipe for Stochastic Gradient MCMC , 2015, NIPS.

[2] Yee Whye Teh,et al. Bayesian Learning via Stochastic Gradient Langevin Dynamics , 2011, ICML.

[3] Qiang Liu,et al. Stein Variational Gradient Descent as Gradient Flow , 2017, NIPS.

[4] Ryan Babbush,et al. Bayesian Sampling Using Stochastic Gradient Thermostats , 2014, NIPS.

[5] David M. Blei,et al. Variational Inference: A Review for Statisticians , 2016, ArXiv.

[6] Dilin Wang,et al. Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm , 2016, NIPS.

[7] Tianqi Chen,et al. Stochastic Gradient Hamiltonian Monte Carlo , 2014, ICML.