Machine Learning Theory
Lecture 1, Jan. 12th 2010
Maria-Florina Balcan
Machine Learning
Image Classification
Document Categorization
Speech Recognition Protein Classification
Branch Prediction
Playing Games
Fraud Detection
Spam Detection
Computational Advertising
2
Goals of Machine Learning Theory
Develop and analyze models to understand:
• what kinds of tasks we can hope to learn, and from what
kind of data
• what types of guarantees might we hope to achieve
• prove guarantees for practically successful algs (when will
they succeed, how long will they take?);
• develop new algs that provably meet desired criteria
Interesting connections to other areas including:
• Algorithms
• Combinatorial Optimization
• Probability & Statistics
• Complexity Theory
• Game Theory
• Information Theory
Example: Supervised Classification
Decide which emails are spam and which are important.
Not spam
Supervised classification
spam
Goal: use emails seen so far to produce good prediction
rule for future data.
4
Example: Supervised Classification
Represent each message by features. (e.g., keywords, spelling, etc.)
example
Reasonable RULES:
Predict SPAM if unknown AND (money OR pills)
Predict SPAM if 2money + 3pills –5 known > 0
label
+ + +
+
- Linearly separable
5
Two Main Aspects of Supervised Learning
Algorithm Design. How to optimize?
Automatically generate rules that do well on observed data.
Confidence Bounds, Generalization Guarantees,
Sample Complexity
Confidence for rule effectiveness on future data.
Well understood for passive supervised learning.
6
Other Protocols for Supervised Learning
• Semi-Supervised Learning
Using cheap unlabeled data in addition to labeled data.
• Active Learning
The algorithm interactively asks for labels of informative examples.
Theoretical understanding severely lacking until a couple of years ago.
Lots of progress recently. We will cover some of these.
• Learning with Membership Queries
• Statistical Query Learning
7
Structure of the Class
• Basic models for supervised learning: PAC and SLT.
• Simple algos and hardness results for supervised learning.
• Standard Sample Complexity Results (VC dimension)
• Weak-learning vs. Strong-learning
• Classic, state of the art algorithms: AdaBoost and SVM.
Structure of the Class
• Modern Sample Complexity Results
• Rademacher Complexity
• Margin analysis of Boosting and SVM
• Incorporating Unlabeled Data in the Learning Process.
• Incorporating Interaction in the Learning Process:
• Active Learning
• Learning with Membership Queries
• Classification noise and the Statistical-Query model
• Learning Real Valued Functions
• Reinforcement Learning
Admin
• Course web page: http://www.cc.gatech.edu/~ninamf/ML10/
• 6 hwk assignments. Exercises/problems (pencil-and-paper
problem-solving variety).
[60%]
• Small project: explore a theoretical question, try some
experiments, or read a paper and explain the idea. Short writeup
and possibly presentation. Small groups ok. [25%]
• Take-home exam. [15%]