On the challenges of learning with inference networks on sparse, high-dimensional data

Abstract

We study parameter estimation in Nonlinear Factor Analysis (NFA) where the generative model is parameterized by a deep neural network. Recent work has focused on learning such models using inference (or recognition) networks; we identify a crucial problem when modeling large, sparse, high-dimensional datasets -- underfitting. We study the extent of underfitting, highlighting that its severity increases with the sparsity of the data. We propose methods to tackle it via iterative optimization inspired by stochastic variational inference \citep{hoffman2013stochastic} and improvements in the sparse data representation used for inference. The proposed techniques drastically improve the ability of these powerful models to fit sparse data, achieving state-of-the-art results on a benchmark text-count dataset and excellent results on the task of top-N recommendation.

arXiv comment14 pages, 3 tables, 11 figures

References in corpus (4)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Variational Lossy Autoencoder
• Importance Weighted Autoencoders

Cited by in corpus (9)

• Variational Autoencoders for Collaborative Filtering
• Semi-Amortized Variational Autoencoders
• A Tutorial on Deep Latent Variable Models of Natural Language
• Amortized Variational Inference: A Systematic Review
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• COIN: COmpression with Implicit Neural representations
• Variational Laplace Autoencoders
• Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
• Control as Hybrid Inference