Table of Contents

Personal List

Meta-resources

• Depth First Learning (depth first expositions into papers. covers all material you need to learn topic)

Normalizing Flows

• Normalizing Flows for Probabilistic Modeling and Inference - recommended by David Duvenaud
• Eric Jang’s tutorial
• Lil Log blog post on Flow Based Deep Generative Models

Control as Inference/ Inference in RL

Papers

• An inference perspective on model-based reinforcement learning
• Reinforcement learning and control as probabilistic inference

Blog Posts

• Blog Post (by Dibya Ghosh (promising UC Berkeley undergrad))

Variational Inference

• Spherical VAE(didactic paper on variational autoencoders)
• KL-Divergence Blog Post (by Dibya Ghosh (promising UC Berkeley undergrad))

Monte Carlo

• MCMC intution for everyone
• Hamiltonian Monte Carlo
  • Hamiltonian Monte Carlo explained (endorsed by Princeton Professor)
    • Langrangian and Hamiltonian dynamics introduction (by Princeton Professor)
  • The beginners guide to Hamiltonian Monte Carlo by PhD Student in Machine Learning

GANs

• Depth First learning - InfoGan

Deep Learning General

• Deep Learning Tricks

Graph Neural Networks

• Graph Representation Learning for Algorithmic Reasoning [1 hour talk]
• Michael Bronstein blog posts
• Theoretical Foundations of Graph Neural Networks [1.25 hr talk]