Problem sets, additional material and prerequisites

Papers for Friday, August 9 presentations

Problem Sets:

• Statistical learning: Problem set 1, Problem set 2, Problem set 3.
• Convex optimization: Problem Set 1.
• Bandits: Problem Set 1.
• Reinforcement learning: Problem set 1, Problem set 2, Problem set 3
• Deep learning: Problem set 1, Problem set 2, Problem set 3.

Additional Material

• Statistical learning lectures:
  • Slides from Lecture IV: McDiarmid's Inequality, Rademacher proof
  • Slides from Lecture V: Boosting toy example, boosting learning curves, analysis of training error, margins movie.
  • Rob Schapire course on Theoretical Machine Learning.

Suggested Prerequisites:

• Linear Algebra (sample course)
• Probability (sample course)
• Multivariable calculus (sample course).
• Real Analysis (sample course).

Online resources about the math of machine learning

• Foundations of Machine Learning, Mehryar Mohri, Afshin Rostamizadeh and Ameet Talwalkar
• Understanding Machine Learning: From Theory to Algorithms, Shai Shalev-Shwartz and Shai Ben-David
• Convex Optimization: Algorithms and Complexity, Sébastien Bubeck
• Theory of Classification: A Survey of Some Recent Advances, Stéphane Boucheron, Olivier Bousquet and Gábor Lugosi
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Sébastien Bubeck and Nicolò Cesa-Bianchi
• Algorithms for Reinforcement Learning, Csaba Szepesvári
• Appendix E (Neural Networks), Principles of Neural Science, Sebastian Seung and Rafael Yuste