SDSC8014 - Online Learning and Optimization

Offering Academic Unit
School of Data Science
Credit Units
Course Duration
One Semester
Course Offering Term*:
Semester B 2021/22

* The offering term is subject to change without prior notice
Course Aims

This course covers the fundamentals and applications of online learning and optimization. Topics include online learning, online convex optimization, competitive analysis, regret analysis, online gradient descent, and online algorithms. Other selective topics include online optimization with prediction, robust optimization, online stochastic optimization, and online optimization with feedbacks. Applications in online learning and optimization in societal systems in the face of input uncertainty will be used to complement the theoretical developments. Students should know about convex optimization, linear algebra, and calculus.

Assessment (Indicative only, please check the detailed course information)

Continuous Assessment: 100%
Examination Duration: 0 hours
Detailed Course Information