# DVAE++: Discrete Variational Autoencoders with Overlapping Transformations

arXiv: https://arxiv.org/abs/1802.04920 · HTML: https://mlsanity.com/paper/1802.04920/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2018.

## Built on by (most cited first, 30 of 32)

- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Controllable and Compositional Generation with Latent-Space Energy-Based Models](https://mlsanity.com/paper/2110.10873/) (2021)
- [Densely connected normalizing flows](https://mlsanity.com/paper/2106.04627/) (2021)
- [DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation](https://mlsanity.com/paper/2204.13031/) (2022)
- [Lossy Image Compression with Quantized Hierarchical VAEs](https://mlsanity.com/paper/2208.13056/) (2022)
- [QARV: Quantization-Aware ResNet VAE for Lossy Image Compression](https://mlsanity.com/paper/2302.08899/) (2023)
- [Classical Planning in Deep Latent Space](https://mlsanity.com/paper/2107.00110/) (2021)
- [DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents](https://mlsanity.com/paper/2407.03300/) (2024)
- [Deep Generative Models for Detector Signature Simulation: A Taxonomic Review](https://mlsanity.com/paper/2312.09597/) (2023)
- [Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments](https://mlsanity.com/paper/2311.04453/) (2023)
- [CaloQVAE : Simulating high-energy particle-calorimeter interactions using hybrid quantum-classical generative models](https://mlsanity.com/paper/2312.03179/) (2023)
- [CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation](https://mlsanity.com/paper/2210.07430/) (2022)
- [Optimizing Hierarchical Image VAEs for Sample Quality](https://mlsanity.com/paper/2210.10205/) (2022)
- [Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models](https://mlsanity.com/paper/2407.04958/) (2024)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)
- [A Non-negative VAE:the Generalized Gamma Belief Network](https://mlsanity.com/paper/2408.03388/) (2024)
- [Conditioned quantum-assisted deep generative surrogate for particle-calorimeter interactions](https://mlsanity.com/paper/2410.22870/) (2024)
- [FusionVAE: A Deep Hierarchical Variational Autoencoder for RGB Image Fusion](https://mlsanity.com/paper/2209.11277/) (2022)
- [Discrete Auto-regressive Variational Attention Models for Text Modeling](https://mlsanity.com/paper/2106.08571/) (2021)
- [Sparse Communication via Mixed Distributions](https://mlsanity.com/paper/2108.02658/) (2021)
- [Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies](https://mlsanity.com/paper/2205.01324/) (2022)
- [Fair Inference for Discrete Latent Variable Models](https://mlsanity.com/paper/2209.07044/) (2022)
- [Clinically Plausible Pathology-Anatomy Disentanglement in Patient Brain MRI with Structured Variational Priors](https://mlsanity.com/paper/2211.07820/) (2022)
- [Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Model](https://mlsanity.com/paper/2303.12302/) (2023)
- [An Introduction to Discrete Variational Autoencoders](https://mlsanity.com/paper/2505.10344/) (2025)
- [On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning](https://mlsanity.com/paper/2506.00136/) (2025)
- [Boltzmann Tuning of Generative Models](https://mlsanity.com/paper/2104.05252/) (2021)
- [β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames](https://mlsanity.com/paper/2211.12627/) (2022)
- [Improved Variational Inference in Discrete VAEs using Error Correcting Codes](https://mlsanity.com/paper/2410.07840/) (2024)
- [From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders](https://mlsanity.com/paper/2507.17255/) (2025)

## Abstract (arXiv)

Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult. We propose a new class of smoothing transformations based on a mixture of two overlapping distributions, and show that the proposed transformation can be used for training binary latent models with either directed or undirected priors. We derive a new variational bound to efficiently train with Boltzmann machine priors. Using this bound, we develop DVAE++, a generative model with a global discrete prior and a hierarchy of convolutional continuous variables. Experiments on several benchmarks show that overlapping transformations outperform other recent continuous relaxations of discrete latent variables including Gumbel-Softmax (Maddison et al., 2016; Jang et al., 2016), and discrete variational autoencoders (Rolfe 2016).