45 citations · 59 across the 11 of their papers we have counts for
6 papers · 1 filter
STANLEY: Stochastic Gradient Anisotropic Langevin Dynamics for Learning Energy-Based Models
Belhal Karimi, Jianwen Xie, Ping Li
We propose in this paper, STANLEY, a STochastic gradient ANisotropic LangEvin dYnamics, for sampling high dimensional data. With the growing efficacy and potential of Energy-Based…
A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference
Jianwen Xie, Yaxuan Zhu, Yifei Xu +2
We study a normalizing flow in the latent space of a top-down generator model, in which the normalizing flow model plays the role of the informative prior model of the generator. W…
Exploration in Model-based Reinforcement Learning with Randomized Reward
Lingxiao Wang, Ping Li
Model-based Reinforcement Learning (MBRL) has been widely adapted due to its sample efficiency. However, existing worst-case regret analysis typically requires optimistic planning,…
A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model
Jianwen Xie, Yaxuan Zhu, Jun Li +1
This paper studies the cooperative learning of two generative flow models, in which the two models are iteratively updated based on the jointly synthesized examples. The first flow…
A Class of Two-Timescale Stochastic EM Algorithms for Nonconvex Latent Variable Models
Belhal Karimi, Ping Li
The Expectation-Maximization (EM) algorithm is a popular choice for learning latent variable models. Variants of the EM have been initially introduced, using incremental updates to…
Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler
Jianwen Xie, Zilong Zheng, Ping Li
Due to the intractable partition function, training energy-based models (EBMs) by maximum likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the gradient o…