Provable Algorithms for Data Mining and Machine Learning

Vincent Cohen-Addad (Google).


Course Summaryy | About the lecturer

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 Universit├ę. Before, I was working at the University of Copenhagen, supported by a Marie Sklodowska-Curie individual fellowship. I did my Ph.D at the D├ępartement d'Informatique de l'├ëcole normale sup├ęrieure under the supervision of Claire Mathieu.