COS 598D: Optimization for Machine Learning
lecture topics and notes
lecture topics and notes
Resources for typing notes: def.tex scribe template file
(this file will be updated throughout the course)
- Lecture 1: Introduction to optimization for machine learning. lecture notes: above text.
notes: chapters 1,2 in text
- Lecture 2: Basic concepts in analysis and optimization . Gradient descent and Stochastic Gradient Descent for ML.
notes: chapters 3 in text, and scribe nots by Paula Gradu
- Lecture 3: Generalization and regret
notes: chapter 4 in text, and scribe notes by Lawrence Thul, and by Diana Cai
- Lecture 4: Regularization and mirrored descent
notes: chapter 5 in text, scribe notes by Geoffrey Roeder
- Lecture 5: Adaptive Regularization
notes: chapter 6 in text, and scribe notes by Bill Huang , and more notes by Fangyin Wei
- Lecture 6: Variance Reduction
notes: chapter 7 in text, and scribe notes by Arushi Gupta, and more by Sulin Liu
- Lecture 7: Projection-free algorithms and the Frank-Wolfe method
notes: chapter 8 in text, and scribe notes by Pranay Manocha
- Lecture 8: Nesterov acceleration
- Lecture 9: Second order methods for machine learning
notes: chapter 9 in text, and scrive notes by Mayee Chen, Ethan Tseng, Edgar Minasyan
- Lecture 10: Hyperparameter optimization (part I) & ask me anything (part II)