Generative Modeling by Estimating Gradients of the Data Distribution | Yang SongIntroduction Existing generative modeling techniques can largely be grouped into two categories based on how they represent probability distributions. likelihood-based models, which directly learn the distribution’s probability density (or mass) function via (approximate) maximum likelihood. Typical likelihood-based models include autoregressive models , normalizing flow models , energy-based mode
Google Colab
https://www.math.chuo-u.ac.jp/lecture_notes_almostwhole.pdf
