Robust Optimization &
Machine Learning
Overview
Short Course
Robust Optimization and Machine Learning
Overview
Laurent El Ghaoui
EECS and IEOR Departments
UC Berkeley
Spring seminar TRANSP-OR, Zinal, Jan. 16-19, 2012
January 16, 2012
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Robust Optimization and Machine Learning Overview, Lecture notes of Machine Learning
An overview of a short course on Robust Optimization and Machine Learning taught by Laurent El Ghaoui at UC Berkeley. The course covers topics such as Robust Optimization and Machine Learning. a skiing problem that can be solved using optimization techniques. The problem involves a skier slaloming down a slope through parallel gates of equal width. mathematical equations and formulas related to the problem. The course is relevant to students interested in optimization and machine learning.
Typology: Lecture notes
2021/2022
1 / 5
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Robust Optimization and Machine Learning Overview and more Lecture notes Machine Learning in PDF only on Docsity!
Machine Learning
Overview
Short Course
Robust Optimization and Machine Learning
Overview
Laurent El Ghaoui
EECS and IEOR Departments
UC Berkeley
Spring seminar TRANSP-OR, Zinal, Jan. 16-19, 2012
Machine Learning
Overview
Course topics
Machine Learning
Overview
Course outline
I Jan. 16:
1. Lecture 1: Optimization models.
2. Lecture 2: Convex optimization.
I Jan. 17: Lecture 3: Optimization models in supervised learning.
I Jan. 18:
1. Lecture 4: Optimization in unsupervised learning.
2. Lecture 5: Robust optimization overview.
I Jan. 19:
1. Lecture 6: Robust optimization in supervised learning.
2. Lecture 7: Sparse optimization for text analytics.
Machine Learning
Overview
Speaking of slopes...
An optimization problem you can think about while skiing
A two-dimensional skier must slalom down a slope by going through n
parallel gates of equal width. The first gate’s middle position is ( 0 , 0 );
the i-th gate is separated by the previous one by a distance σ^2 i. We
assume that the skier comes from uphill situated very far away from
the start of the gate, with its initial direction set at a given angle.
N = 5
minimize k^ N=1 (zk − zk− 1 )^2 subject to |zk − yk| ≤ σk, i = 1,... , N P 12 xT^ P x + qT^ x + r P =