20 citations · 22 across the 2 of their papers we have counts for
Showing stat.MLShow all
3 papers · 1 filter
stat.ML2019★ 2 cited
Understanding MCMC Dynamics as Flows on the Wasserstein Space
Chang Liu, Jingwei Zhuo, Jun Zhu
It is known that the Langevin dynamics used in MCMC is the gradient flow of the KL divergence on the Wasserstein space, which helps convergence analysis and inspires recent particl…
stat.ML2018
Understanding and Accelerating Particle-Based Variational Inference
Chang Liu, Jingwei Zhuo, Pengyu Cheng +3
Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian inference literature, for their capacity to yield flexible and accurate approximations.…
stat.ML2017★ 20 cited
Riemannian Stein Variational Gradient Descent for Bayesian Inference
Chang Liu, Jun Zhu
We develop Riemannian Stein Variational Gradient Descent (RSVGD), a Bayesian inference method that generalizes Stein Variational Gradient Descent (SVGD) to Riemann manifold. The be…