Machine Learning Summer School 2008 - Kioloa

Online Learning, Regret Minimization, and Game Theory

author: Avrim Blum, Carnegie Mellon University

Description

The first part of tha tutorial will discuss adaptive algorithms for making decisions in uncertain environments (e.g., what route should I take to work if I have to decide before I know what traffic will like today?) and connections to central concepts in game theory (e.g., what can we say about how traffic will behave overall if everyone is adapting their behavior in such a way?). He will discuss the notions of external and internal regret, algorithms for "combining expert advice" and "sleeping experts" problems, algorithms for implicitly specified problems, and connections to game-theoretic notions of Nash and correlated equilibria. The second part of tha tutorial will be about some recent work on learning with similarity functions that are not necessarily legal kernels. The high-level question here is: if you have a measure of similarity between data points, how closely related does it have to be to your classification problem in order to be useful for learning?

Categories

Top: Computer Science: Machine Learning: On-line Learning
Top: Mathematics: Game Theory

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Online Learning and Game v + On Learning with Similarity Functions
2:08	Plan for the tour:
4:46	Some books/references:
7:40	Stop 1: Online learning, minimizing regret, and combining expert advice
7:52	Consider the following setting…
10:36	“No-regret” algorithms for repeated decisions (1)
13:09	“No-regret” algorithms for repeated decisions (2)
14:40	Some intuition & properties of no-regret algs. (1)
17:28	Some intuition & properties of no-regret algs. (2)
19:03	History and development (abridged) (1)
22:38	History and development (abridged) (2)
25:29	To think about this, let’s look at the problem of “combining expert advice”.
25:41	Using “expert” advice
27:58	Simpler question
31:22	Using “expert” advice
33:07	Weighted Majority Algorithm
34:13	Analysis: do nearly as well as best expert in hindsight
38:17	Randomized Weighted Majority
41:58	Analysis
46:51	Summarizing
48:59	What if we have N options, not N predictors? (1)
51:54	What if we have N options, not N predictors? (2)

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.