-
WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
To train an inference network jointly with a deep generative topic model...
03/04/2018 ∙ by Hao Zhang, et al. ∙
0
∙
share
read it
-
Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection
Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have rece...
02/07/2020 ∙ by Qifan Song, et al. ∙
0
∙
share
read it
-
Scalable MCMC for Mixed Membership Stochastic Blockmodels
We propose a stochastic gradient Markov chain Monte Carlo (SG-MCMC) algo...
10/16/2015 ∙ by Wenzhe Li, et al. ∙
0
∙
share
read it
-
Fisher Information and Natural Gradient Learning of Random Deep Networks
A deep neural network is a hierarchical nonlinear model transforming inp...
08/22/2018 ∙ by Shun-ichi Amari, et al. ∙
0
∙
share
read it
-
Scalable Data Augmentation for Deep Learning
Scalable Data Augmentation (SDA) provides a framework for training deep ...
03/22/2019 ∙ by Yuexi Wang, et al. ∙
4
∙
share
read it
-
Dirichlet Variational Autoencoder
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a D...
01/09/2019 ∙ by Weonyoung Joo, et al. ∙
0
∙
share
read it
-
The Poisson Gamma Belief Network
To infer a multilayer representation of high-dimensional count vectors, ...
11/06/2015 ∙ by Mingyuan Zhou, et al. ∙
0
∙
share
read it
Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC
06/06/2017 ∙ by Yulai Cong, et al. ∙
0
∙
share
It is challenging to develop stochastic gradient based scalable inference for deep discrete latent variable models (LVMs), due to the difficulties in not only computing the gradients, but also adapting the step sizes to different latent factors and hidden layers. For the Poisson gamma belief network (PGBN), a recently proposed deep discrete LVM, we derive an alternative representation that is referred to as deep latent Dirichlet allocation (DLDA). Exploiting data augmentation and marginalization techniques, we derive a block-diagonal Fisher information matrix and its inverse for the simplex-constrained global model parameters of DLDA. Exploiting that Fisher information matrix with stochastic gradient MCMC, we present topic-layer-adaptive stochastic gradient Riemannian (TLASGR) MCMC that jointly learns simplex-constrained global parameters across all layers and topics, with topic and layer specific learning rates. State-of-the-art results are demonstrated on big data sets.
READ FULL TEXT
Comments
There are no comments yet.