463 citations · 5.1k across the 190 of their papers we have counts for
10 papers · 2 filters
Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
Chunyuan Li, Changyou Chen, David Carlson +1
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods addre…
High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
Chunyuan Li, Changyou Chen, Kai Fan +1
Learning in deep models using Bayesian methods has generated significant attention recently. This is largely because of the feasibility of modern Bayesian methods to yield scalable…
Learning a Hybrid Architecture for Sequence Regression and Annotation
Yizhe Zhang, Ricardo Henao, Lawrence Carin +2
When learning a hidden Markov model (HMM), sequen- tial observations can often be complemented by real-valued summary response variables generated from the path of hid- den states.…
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
Changyou Chen, David Carlson, Zhe Gan +2
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied. We exp…
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
Zhe Gan, Chunyuan Li, Ricardo Henao +2
Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmo…
Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data
Changwei Hu, Piyush Rai, Changyou Chen +2
We present a Bayesian non-negative tensor factorization model for count-valued tensor data, and develop scalable inference algorithms (both batch and online) for dealing with massi…
Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors
Changwei Hu, Piyush Rai, Lawrence Carin
We present a scalable Bayesian model for low-rank factorization of massive tensors with binary observations. The proposed model has the following key properties: (1) in contrast to…
Variational Gaussian Copula Inference
Shaobo Han, Xuejun Liao, David B. Dunson +1
We utilize copulas to constitute a unified framework for constructing and optimizing variational proposals in hierarchical Bayesian models. For models with continuous and non-Gauss…
Non-Gaussian Discriminative Factor Models via the Max-Margin Rank-Likelihood
Xin Yuan, Ricardo Henao, Ephraim L. Tsalik +2
We consider the problem of discriminative factor analysis for data that are in general non-Gaussian. A Bayesian model based on the ranks of the data is proposed. We first introduce…
A Generative Model for Deep Convolutional Learning
Yunchen Pu, Xin Yuan, Lawrence Carin
A generative model is developed for deep (multi-layered) convolutional dictionary learning. A novel probabilistic pooling operation is integrated into the deep model, yielding effi…