Summary of Hierarchical Vae with a Diffusion-based Vampprior, by Anna Kuzina et al.
Hierarchical VAE with a Diffusion-based VampPrior
by Anna Kuzina, Jakub M. Tomczak
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior), a novel approach to deep hierarchical variational autoencoders. The proposed method applies amortization to scale the VampPrior, allowing for better performance compared to original VampPrior work and other deep hierarchical VAEs while using fewer parameters. The paper demonstrates improved training stability and latent space utilization on benchmark datasets such as MNIST, OMNIGLOT, and CIFAR10. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to make deeper and more powerful models called Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). The model uses something called amortization to help it work better. This means that the model can do its job well even when there are many layers, which makes it useful for certain tasks. The paper shows that this new approach works better than other similar models and is more stable during training. It also helps create a clearer picture of what’s going on inside the model. |
Keywords
» Artificial intelligence » Diffusion » Latent space
