Presentation

Presentation

This 2-week summer school will focus on optimization for machine learning.

Dates : June, 3^rd -14^th, 2019

The summer school takes place on INSA Campus in Toulouse.

The aim of this series of Lectures is to provide the basic background for dealing with Optimization issues in deterministic and stochastic environment.

More specifically, we address the main features of smooth optimization algorithms with and without constraints : in addition to the theoretical material, we describe deterministic and stochastic gradient algorithms, Newton-type algorithms, least square algorithms. This part will be completed by an introduction to nonsmooth optimization algorithms (sub gradient algorithms and proximal algorithms). All these optimization algorithms will be implemented during practice classes with application to image processing. The second part of the Lectures will be devoted to actual Statistical issues related to Machine Learning.

Admission

Access condition

This program is dedicated to students having a L3 or M1 degree.

Deadline registration : March 18th, 2019

Prerequisites

Differential calculus, basics in statistics.

Application must be made directly to the organizing institution. No application is possible through this website. Please click on the link "See the course website" to find out how to apply.

Program

Training content

Learning objectives

• To be able to choose and implement a suitable algorithm for solving a given optimization problem, especially in the context of machine learning.

Contents

• Optimality conditions
  
  
• Algorithms for differentiable optimization without constraints

1. Gradient algorithms
2. Stochastic gradient algorithm
3. Newton-type algorithms
4. Least squares issues
   
   

• First algorithms for nondifferentiable optimization - LASSO, proximal algorithm.
  
  
• Introduction to Statistical Learning: Ridge Regression, Lasso, Support Vector Machines
  
  
• Imaging applications: image registration, compressive sampling, dictionary training, ...