Contains all the sources I have used to build VAE
- Tutorial on Variational Autoencoders By Carl Doersch
- Variational Inference with Normalizing Flows By Resende and Mohamed (google/DeepMind)
- Auto-encoding Variational Bayes By Kingma and Welling
- An Introduction to Variational AutoEncoders by Kingma and Welling
- An extended version of their seminal paper on VAE
- GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection System
- Normalizing Flows: An Introduction and Review of Current Methods By Koyzev, Simon, Brubaker (2020)
- beta-VAE:Learning Basic Visual Concepts with a Constrained Variational Framework by Higgins, Matthey, Pal, Burgess, Glorot, Botvinick, Mohamed, Lerchner (DeepMind)
- Hands-On Bayesian Neural Network-A tutorial bfor Deep Learning Users
- Data Augmentation in HDLSS with VAE
- This is a very nice paper in terms of how easily it explained some of the complicated stuff on how to improve upon the traditional VAE. More importantly, it contains lots of references to other papers that tried to improve modeling of the data distribution as well as moving away from traditional gaussian prior. Must read (even if some of the Reimannian Metric stuff is not clear).
- Variational Autoencoder By Jeremy Bernstein
- Black-box Variational Inference via the reparameterization gradient By Jeremy Bernstein
- Variational Inference By Jeremy Bernstein
- Note: These blogs by Jeremey Bernstein contains mathematical discussion on variational autoencoder and why it is called variational and so forth. Nice one.
- Totorial#5: Variational Autoencoder By Borealis AI
- [A Step Up with Variational AutoEncoders] (https://jaketae.github.io/study/vae/) By Jake Tae
- Note: Other blog posts by Jake Tae are very informative
- From ELBO to DDPM By Jake Tae
- DDPM stands for Denoising Diffusion Probabilistic Models
- Variational AutoEncoders
- Slides
- Understanding KL-Divergence By Nipun Batra
- Bayesian Linear Regression by Nipur Batra
- A quick intro to Bayesian Neural networks By Matthew McAteer
- Understanding The Variational Lower Bounds By Xiton Yang
- What is Variational Autoencoders? By Christian Versloot
- Variational Autoencoders By Jeremy Jordon
- Notes: The resources mentioned at the end of this blog is priceless.
- Building Variational Autoencoders in Tensorflow By Danijar Hafner
- Tutorial- What is a Variational AutoEncoder? By Jaan Altosaar
- This is the github repo
- Density Estimation: Variational Autoencoders By Rui Shu
- KL-Divergence Explained
- Variational Inference with Normalizing Flows by Jennifer Ngadiuba (caltech) ML Journal Club
- Normalizing Flows
- Normalizing Flows Tutorial By Eric Jang
- A Tutorial on VAE with Concise Keras Implementation By Louis Tiao
- Implementating VAE in Keras:Beyond the QuickStart Tutorial By Louis Tiao
- Simple and Effective VAE Training with Calibrated Decoders by Rybkin, Daniildis and Levin
- Understanding VAEs By Joseph Rocca
- From AE to Beta-VAE By Lil'Log
- Note Her other posts on Diffusion models and ML in general is very informatave.
- Evidence, KL-divergence, and ELBO By Massimiliano Patacchiola
- A good read on ELBO. Read his other posts as well.
- Variational Inference in Bayesian Neural Network By Martin Krasser
- Tensorflow-Probability + Keras
- Pyro: Variational AE
- Note: VAE in pytorch
- VAE_BENCHMARK
- Has a lot of resources. Look at it's Readme page. Also, there are a lot of different VAE models implemented in PyTorch along with different samplers.