2020/03/03 by Alex Nichol, Nichol, Alex
Computer Science · Mathematics · #Anomaly Detection Techniques and Applications #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Time Series Analysis and Forecasting #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2003.01599
arxiv created 2020/03/03 · openalex publication_date 2020/03/03 · arxiv updated 2020/03/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, I present VQ-DRAW, an algorithm for learning compact discrete representations of data. VQ-DRAW leverages a vector quantization effect to adapt the sequential generation scheme of DRAW to discrete latent variables. I show that VQ-DRAW can effectively learn to compress images from a variety of common datasets, as well as generate realistic samples from these datasets with no help from an autoregressive prior.