Teaching

Machine Learning

  1. Policy Optimization and RL Algorithms

  2. A Note about KL Divergence

  3. A Taxonomy of Reinforcement Learning Algorithms

  4. Monte Carlo Tree Search

  5. How do Mixture of Expert Models Work?

ML Systems

  1. ML at Scale: Pipeline Parallelism

  2. ML at Scale: Tensor Parallelism

  3. ML at Scale: Data Parallelism

Notes

  1. Introduction to RL

  2. Archive: The Daily Ink Paper Breakdowns

  3. Probability and Random Processes Cheat Sheet