Provable Algorithms for Data Mining and Machine Learning

Vincent Cohen-Addad (Google).


Course Summary | About the lecturer | Location and schedule

Registration form:

Register here

Course summary:

Data mining and machine learning tools are at the heart of large number of computer science applications, in both academic and industrial worlds. Thus, designing efficient and scalable algorithms for problems arising in these contexts is a central research question. In this course, we will present algorithms with provable guarantees for several of these applications (e.g.: clustering), and in several contexts (e.g.: differential-privacy).

About the lecturer:

I am a Research Scientist at Google Research. The focus of my research is on the design of algorithms for clustering and network design problems, with an emphasis on problems arising in data analysis and machine learning contexts. My goal is to come up with efficient algorithms and understand the complexity of these problems. I have also a strong interest in online optimization, learning theory, computational geometry and fixed-parameter and fined-grained complexity. Before joining Google I was a CNRS researcher at Sorbonne Université. Before, I was working at the University of Copenhagen, supported by a Marie Sklodowska-Curie individual fellowship. I did my Ph.D at the Département d'Informatique de l'École normale supérieure under the supervision of Claire Mathieu.

Materials: Homework   Day 1 (paper)   Day 2 (handwritten notes)

Location and schedule:

Wednesday, March 1st in 5440
14:15 - 15:45 lecture
16:15 - 17:45 class
Thursday, March 2nd in 5440
14:15 - 15:45 lecture
16:15 - 17:45 class