CODE | 108960 |
---|---|
ACADEMIC YEAR | 2022/2023 |
CREDITS |
|
SCIENTIFIC DISCIPLINARY SECTOR | MAT/09 |
TEACHING LOCATION |
|
SEMESTER | 2° Semester |
TEACHING MATERIALS | AULAWEB |
The course will illustrate the basic tools needed to understand and use the main optimization and operationa research algorithms, relevant to solve machine learning and inverse problems.
The goal of the course is to provide tools for a theoretical understanding and a practical usege of linear programming and the main convex optimization algorithms used in machine learning and inverse problems.
At the end of the course the students will have a working knowledge of convex optimzation and linear programming. In particular, to provide skills to: Recognize convex problems, understand and use convex optimization algorithms, solve convex problems in real scenarios.
Calculus for functions of several variables, linear algebra, probability
Classes on the blackboard and labs
The course will cover the basic notions for optimization problems. It will cover the linear programming problem, and optimization algorithms for the minimization of smooth and nonsmooth convex functions. The course will discuss the convergence properties of gradient descent, stochastic gradient descent and proximal gradient descent. Applications to machine learning and imaging problems will be implemented and used during the lab sessions.
S. Boyd and L. Vandenberghe, Convex Optimization, Cambridge University Press, 2004
S. Bubeck, Convex Optimization: Algorithms and Complexity, https://arxiv.org/abs/1405.4980?context=cs
S. Salzo, S. Villa, Proximal Gradient Methods for Machine Learning and Imaging, 2022
Office hours: By appointment wich can be fixed in person or via email : silvia.villa@unige.it
SILVIA VILLA (President)
ERNESTO DE VITO
CESARE MOLINARI (Substitute)
According to the academic calendar
All class schedules are posted on the EasyAcademy portal.
To pass the exam the student have to present a short report. The student can choose one among the following options:
The report preparation and its discussion are aimed at verifying the student's achievement of an independent critical reasoning capability in the context of machine learning.
During the report presentation, basic questions d on the topics covered by the course amy be asked.