# Stick-Breaking Variational Autoencoders

arXiv: https://arxiv.org/abs/1605.06197 · HTML: https://mlsanity.com/paper/1605.06197/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2016.

## Built on by (most cited first, 30 of 44)

- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Priors in Bayesian Deep Learning: A Review](https://mlsanity.com/paper/2105.06868/) (2021)
- [PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior](https://mlsanity.com/paper/2106.06406/) (2021)
- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [Variable-rate discrete representation learning](https://mlsanity.com/paper/2103.06089/) (2021)
- [Differentiable Causal Discovery Under Latent Interventions](https://mlsanity.com/paper/2203.02336/) (2022)
- [t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence](https://mlsanity.com/paper/2312.01133/) (2023)
- [SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge](https://mlsanity.com/paper/2208.11266/) (2022)
- [Amortized Variational Inference: A Systematic Review](https://mlsanity.com/paper/2209.10888/) (2022)
- [Cauchy-Schwarz Regularized Autoencoder](https://mlsanity.com/paper/2101.02149/) (2021)
- [Concept Graph Neural Networks for Surgical Video Understanding](https://mlsanity.com/paper/2202.13402/) (2022)
- [Model Selection for Bayesian Autoencoders](https://mlsanity.com/paper/2106.06245/) (2021)
- [Coupled Gradient Estimators for Discrete Latent Variables](https://mlsanity.com/paper/2106.08056/) (2021)
- [Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes](https://mlsanity.com/paper/2302.04534/) (2023)
- [Diffusion Models with Deterministic Normalizing Flow Priors](https://mlsanity.com/paper/2309.01274/) (2023)
- [Deep Adaptive Multi-Intention Inverse Reinforcement Learning](https://mlsanity.com/paper/2107.06692/) (2021)
- [Bayesian Nonparametrics for Offline Skill Discovery](https://mlsanity.com/paper/2202.04675/) (2022)
- [A Non-negative VAE:the Generalized Gamma Belief Network](https://mlsanity.com/paper/2408.03388/) (2024)
- [Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation](https://mlsanity.com/paper/2102.06143/) (2021)
- [Stabilizing the Kumaraswamy Distribution](https://mlsanity.com/paper/2410.00660/) (2024)
- [ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE](https://mlsanity.com/paper/2107.09286/) (2021)
- [ClusterDDPM: An EM clustering framework with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2312.08029/) (2023)
- [On Kernel-based Variational Autoencoder](https://mlsanity.com/paper/2405.12783/) (2024)
- [BN-Pool: Bayesian Nonparametric Pooling for Graphs](https://mlsanity.com/paper/2501.09821/) (2025)
- [Meta-learning representations for clustering with infinite Gaussian mixture models](https://mlsanity.com/paper/2103.00694/) (2021)
- [Variational Auto Encoder Gradient Clustering](https://mlsanity.com/paper/2105.06246/) (2021)
- [Unsupervised Image Generation with Infinite Generative Adversarial Networks](https://mlsanity.com/paper/2108.07975/) (2021)
- [DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder](https://mlsanity.com/paper/2305.14067/) (2023)
- [A Metalearned Neural Circuit for Nonparametric Bayesian Inference](https://mlsanity.com/paper/2311.14601/) (2023)
- [The VampPrior Mixture Model](https://mlsanity.com/paper/2402.04412/) (2024)

## Abstract (arXiv)

We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesian nonparametric version of the variational autoencoder that has a latent representation with stochastic dimensionality. We experimentally demonstrate that the SB-VAE, and a semi-supervised variant, learn highly discriminative latent representations that often outperform the Gaussian VAE's.