|
HU Credits:
2
Degree/Cycle:
2nd degree (Master)
Responsible Department:
computer sciences
Semester:
2nd Semester
Teaching Languages:
Hebrew
Campus:
E. Safra
Course/Module Coordinator:
Alon Gonen
Coordinator Office Hours:
Teaching Staff:
Mr. Gonen Alon
Course/Module description:
We will study modern approaches in optimization while focusing on important applications in Machine Learning.
Course/Module aims:
1. Getting familiar with families of optimization problems which can be solved efficiently. Understanding the corresponding optimization methods.
2. Understanding the trade-off between computational simplicity and convergence rate.
3. Understanding the role of the geometry of the problem. How can we “learn” the geometry?
4. Understanding the role of randomness: sidestepping computational hardness and coping with limited information.
Learning outcomes - On successful completion of this module, students should be able to:
Formulating optimization problems and designing efficient methods for solving these problems
Attendance requirements(%):
Teaching arrangement and method of instruction:
Course/Module Content:
1. Review of basic (deterministic) first and second-order methods
2. Interior point methods
3. Stochastic and online optimization in Machine Learning
4. Optimization in the distributed setting
Required Reading:
-
Additional Reading Material:
Will be provided
Course/Module evaluation:
End of year written/oral examination 70 %
Presentation 0 %
Participation in Tutorials 0 %
Project work 0 %
Assignments 30 %
Reports 0 %
Research project 0 %
Quizzes 0 %
Other 0 %
Additional information:
|
