Exponential-Min and Gumbel-Max
Exponential-min and Gumbel-max tricks for reformulating sampling from a discrete distribution as argmin and argmax, making the sampling operation differentiable.
Machine Learning
Posts and notes on Machine Learning.
Recent Progress in Language Modeling
This page is a high-level summary / notes of various recent results in language modeling with little explanations
Recent Progress in Neural Variational Inference
A literature survey of recent papers on Neural Variational Inference (NVI) and its application in topic modeling.
A Brief Survey of Generative Models
A high-level summary of various generative models including Variational Autoencoders (VAE), Generative Adverserial Networks (GAN), and their notable extentions and generalizations, such as f-GAN, Adversarial Variational Bayes (AVB), Wasserstein GAN, Wasserstein Auto-Encoder (WAE), Cramer GAN and etc
EM Algorithm in 10 minutes
A quick walk-through of Expectation-Maximization (EM) algorithm and its cousins.