Foundations of Machine Learning
Lecture 8
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Regression
Mehryar Mohri - Foundations of Machine Learning
page 2
Regression Problem
Training data: sample drawn i.i.d. from set X
according t
Foundations of Machine Learning
Lecture 9
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Multi-Class Classication
Mehryar Mohri - Foundations of Machine Learning
page 2
Motivation
Real-world problems often have multiple classes:
te
Foundations of Machine Learning
Lecture 4
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Support Vector Machines
Mehryar Mohri - Foudations of Machine Learning
This Lecture
Support Vector Machines - separable case
Support Vector
Foundations of Machine Learning
Lecture 5
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Kernel Methods
Motivation
Non-linear decision boundary.
Efcient computation of inner products in high
dimension.
Flexible selection of mor
Foundations of Machine Learning
Lecture 6
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Boosting
Mehryar Mohri - Foundations of Machine Learning
page 2
Weak Learning
(Kearns and Valiant, 1994)
Denition: concept class C is weakly
Foundations of Machine Learning
Lecture 7
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
On-Line Learning
Mehryar Mohri - Foundations of Machine Learning
page 2
Motivation
PAC learning:
distribution xed over time (training and test
Foundations of Machine Learning
Lecture 2
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
PAC Learning
Concentration Bounds
Motivation
Some computational learning questions
What can be learned efciently?
What is inherently hard
Foundations of Machine Learning
Lecture 10
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Ranking
Mehryar Mohri - Foundations of Machine Learning
page 2
Motivation
Very large data sets:
too large to display or process.
limited
Foundations of Machine Learning
Lecture 3
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Learning Bounds for
Innite Hypothesis Sets
Motivation
With an innite hypothesis set H, the error bounds
of the previous lecture are not inform
Foundations of Machine Learning
Lecture 1
Mehryar Mohri
Courant Institute and Google Research
mohri@cims.nyu.edu
Logistics
Prerequisites: basics in linear algebra, probability,
and analysis of algorithms.
Workload: about 3-4 homework assignments +
proj