DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors

Abstract

Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches for relaxing Boltzmann machines to continuous distributions that permit training with importance-weighted bounds. These relaxations are based on generalized overlapping transformations and the Gaussian integral trick. Experiments on the MNIST and OMNIGLOT datasets show that these relaxations outperform previous discrete VAEs with Boltzmann priors. An implementation which reproduces these results is available at https://github.com/QuadrantAI/dvae .

arXiv commentNeural Information Processing Systems (NIPS) 2018

Cited by in corpus (14)

• NVAE: A Deep Hierarchical Variational Autoencoder
• Lossy Image Compression with Quantized Hierarchical VAEs
• Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow
• Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
• PixelVAE++: Improved PixelVAE with Discrete Prior
• Score-based Generative Modeling in Latent Space
• Discrete Representations Strengthen Vision Transformer Robustness
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• Context-aware learning for generative models
• VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models
• Improved Gradient-Based Optimization Over Discrete Distributions
• Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
• The LORACs prior for VAEs: Letting the Trees Speak for the Data
• Learning Latent Space Energy-Based Prior Model