Consultation hours

Course

Send me an email to schedule an appointment online.
 
Modern Methods of Decision Making
Master Program 
  • Data Science  
Meetings
  • Mondays, from 11:10 to 14:20, from January 11 to June 14, 2021
Format
  • Online
  • Zoom link: here
  • pwd: come_in
Telegram channel
Main references for the course:
  •  S. Shalev-Shwartz and S. Ben-David (2014). Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press.
  • S. Bubeck (2015). Convex Optimization: Algorithms and Complexity. Foundations and Trends in Machine Learning. Vol. 8, No. 3-4.
  • E. Hazan (Book in Preparation). Introduction to Online Convex Optimization. Available here
Home assignments
  • Home assignement 3: Due April 26
Teaching material
  • Lecture notes, seminars, home assignments and video recordings: here
Previously:
  • Lecture 0: Introduction 
  • Lecture 1:  Statistical vs. online learning
  • Lecture 2: Tools from probability theory 
  • Lecture 3:  Recap on linear algebra and differential calculus
  • Lecture 4: Convexity
  • Lecture 5: Empirical risk minimisation I
  • Lecture 6: Empirical risk minimisation II
  • Lecture 7: Convex approach to binary classification
  • Lecture 8: Gradient descent I
  • Lecture 9: Gradient descent II
  • Lecture 10: Mirror descent I
  • Lecture 11: Mirror descent II
Next: 
  • Lecture 12: Stochastic optimization (May 17)
  • Lecture 13: Introduction to online learning
  • Lecture 14: Prediction with expert advice
  • Lecture 15: First order methods for online convex optimisation
  • Lecture 16: Online newton step algorithm
  • Lecture 17: Stochastic bandit algorithms
  • Lecture 18: Adversarial bandit algorithms
  • Lecture 19: Bandit convex optimisation

Course

Gradients flows in metric spaces
PhD Program
Meetings
  • Thursdays, from 18:10 to 21:00, from January 14 to March 18, 2021
Format
  • Online
  • Zoom link: here
  • pwd: come_in
Telegram channel
References for the course
  • S. Danieri and G. Savaré (2014). Lecture notes on gradient flows and optimal transport. In Y. Ollivier, H. Pajot, & C. Villani (Eds.), Optimal Transport: Theory and Applications (London Mathematical Society Lecture Note Series, pp. 100-144). Cambridge: Cambridge University Press. (available on arxiv here)
  • L. Ambrosio, N. Gigli and G. Savaré (2005). Gradient Flows. Birkhauser.
  • L. Ambrosio and N. Gigli (2009). A user’s guide to optimal transport. (available here
Teaching material
  • Lecture notes: coming soon
Previously
  • Lecture 0: Intro 
  • Lecture 1: Review of gradient flows in Euclidean spaces 
  • Lecture 2: Definitions of gradient flows in metric spaces: EDI, EDE and EVI​​
  • Lectures 3 and 4: Existence and uniqueness of gradient flows
  • Lecture 5: Optimal transport I
Next​
  • Lecture 6: Optimal transport II (April 15)