20 citations · 74 across the 19 of their papers we have counts for
19 papers
Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
Weixin Wang, Haoyang Zheng, Guang Lin +2
Langevin-based Thompson Sampling (TS) methods for multi-armed bandits use likelihood gradients to approximate posterior samples when exact sampling is intractable. As new rewards a…
Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory
Jiajun Liang, Qian Zhang, Wei Deng +2
This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimat…
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…
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
Haoyang Zheng, Wei Deng, Christian Moya +1
Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounter…
Non-convex Bayesian Learning via Stochastic Gradient Markov Chain Monte Carlo
Wei Deng
The rise of artificial intelligence (AI) hinges on the efficient training of modern deep neural networks (DNNs) for non-convex optimization and uncertainty quantification, which bo…
Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation
Yu Chen, Wei Deng, Shikai Fang +7
The Schrödinger bridge problem (SBP) is gaining increasing attention in generative modeling and showing promising potential even in comparison with the score-based generative model…