2 citations · 2 across the 8 of their papers we have counts for
4 papers · 1 filter
Optimal Stochastic Trace Estimation in Generative Modeling
Xinyang Liu, Hengrong Du, Wei Deng +1
Hutchinson estimators are widely employed in training divergence-based likelihoods for diffusion models to ensure optimal transport (OT) properties. However, this estimator often s…
Exploring Non-Convex Discrete Energy Landscapes: An Efficient Langevin-Like Sampler with Replica Exchange
Haoyang Zheng, Hengrong Du, Ruqi Zhang +1
Gradient-based Discrete Samplers (GDSs) are effective for sampling discrete energy landscapes. However, they often stagnate in complex, non-convex settings. To improve exploration,…
Non-Reversible Langevin Algorithms for Constrained Sampling
Hengrong Du, Qi Feng, Changwei Tu +2
We consider the constrained sampling problem where the goal is to sample from a target distribution on a constrained domain. We propose skew-reflected non-reversible Langevin dynam…
Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
Haoyang Zheng, Hengrong Du, Qi Feng +2
Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler for non-convex learning in large-scale datasets. However, the simulation may encounter stagn…