Courses – Fakultet tehničkih nauka u Novom Sadu

Subject: Distributed optimization for big data with privacy aware learning (17.DE424)

Type of studies	Title
Doctoral Academic Studies	Power, Electronic and Telecommunication Engineering (Year: 2, Semester: Winter)

General information:

Category	Scientific-professional
Scientific or art field	Telecommunications and Signal Processing
ECTS	10

The goal of the course is to introduce students to basic principles of distributed optimization, state-of-the art algorithms in this area and their applications, and privacy aware machine learning. Through course project, students will have the opportunity to conduct scientific research in a targeted area of distributed optimization, relevant for student's future PhD thesis.

After successful completion of the course, students will be able to apply the covered algorithms on given optimization, i.e., machine learning problems, and thereby solve them in distributed fashion without compromising data privacy.

- basic principles of distributed optimization - gradient and subgradient method - optimal first order methods - dual decomposition, alternating direction method of multipliers (ADMM) - second order methods: Newton and approximate Newton - stochastic optimization, stochastic approximation - sampling methods - privacy aware learning: local and differential privacy

lectures, consultations, student's independent scientific research, course project

Authors	Title	Year	Publisher	Language
S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein	Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers	2011	Foundations and Trends in Machine Learning, 3(1):1–122	English
Dimitri P. Bertsekas	Nonlinear Programming	2016	Athena Scientific; 3rd edition	English
Dimitri P. Bertsekas, John N. Tsitsikli<\eng>	Parallel and Distributed Computation: Numerical Methods<\eng>	1989	Prentice Hall<\eng>	English
Angelia Nedic, Asu Ozdaglar<\eng>	Cooperative Distributed Multi-Agent Optimization<\eng>, poglavlje u knjizi Convex Optimization in Signal Processing and Communications, Y. Eldar, D. Palomar (Eds.)<\eng>	2010	Cambridge University Press<\eng>	English