Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC

by   Yulai Cong, et al.

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.


page 1

page 2

page 3

page 4


WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling

To train an inference network jointly with a deep generative topic model...

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

Hierarchical topic models such as the gamma belief network (GBN) have de...

Fisher Information and Natural Gradient Learning of Random Deep Networks

A deep neural network is a hierarchical nonlinear model transforming inp...

AdaGeo: Adaptive Geometric Learning for Optimization and Sampling

Gradient-based optimization and Markov Chain Monte Carlo sampling can be...

Scalable Data Augmentation for Deep Learning

Scalable Data Augmentation (SDA) provides a framework for training deep ...

High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models

Learning in deep models using Bayesian methods has generated significant...

Practical Riemannian Neural Networks

We provide the first experimental results on non-synthetic datasets for ...