EP3260: Fundamentals of Machine Learning Over Networks

This course covers fundamentals of machine learning over networks (MLoNs). It starts from a conventional single-agent setting where one server runs a convex/non-convex optimization problem to learn an unknown function. We introduce several approaches to address this seemingly, simple yet fundamental, problem. We introduce an abstract form of MLoNs, present centralized and distributed solution approaches to address this problem, and exemplify via training a deep neural network over a network. The course covers various important aspects of MLoNs, including optimality, computational complexity, communication complexity, security, large-scale learning, online learning, MLoN with partial information, and several application areas. As most of these topics are under heavy researches nowadays, the course is not based on a single textbook but builds on a series of key publications in the field. The course also includes a two-days workshop on recent advancements on fundamentals of MLoNs.

Students will be grouped for homework and computer assignments. Special topic sessions are in the format of a two-days workshop, where students will present (both oral presentation and posters) some key publications of the field. A basic knowledge of convex optimization and probability theory is required to follow the course.

Announcements


  • Invited talks are now available at our YouTube channel.
  • Deadline for the last two CAs is extended to April 12, 2019. Will not be extended anymore.
  • Workshop website is up! Check the program and Stident Group schedules.
  • CAs 5 and 6 are available here. Deadline end of March.
  • Deadline extension for CA4. New deadline is Friday March 1, 2019, 18:00 CET.
  • Deadline extension for HW3. New deadline is Friday Feb 22, 2019, 18:00 CET.
  • Check out our course Github account. You should upload your HW, CAs, and peer-reviews there.
  • Videos are being posted in our YouTube playlist
  • Deadline of CAs are 14 days.
  • Deadline of HW is 7 days.
  • Slides of Lecture 3 is up.
  • Deadline of HW1: Jan. 30, 2019, 10:00.
  • Now, you can remotely attend the lectures via this link. It will be active 5 minutes before every lecture.
  • Slides of Lecture 2 is up.
  • The first lecture will be on Jan. 16, 2019, 10:00 - 12:00 in Q2, KTH Main Campus.
  • See here for the full schedule
  • Registration is open. Register Here