Agnostic Active Learning

author: John Langford, Microsoft Research
published: Feb. 25, 2007,   recorded: July 2006,   views: 1024
Categories

Slides

Related content

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.
Lecture popularity: You need to login to cast your vote.
  Bibliography

Description

The great promise of active learning is that via interaction the number of samples required can be reduced to logarithmic in the number required for standard batch supervised learning methods. To achieve this promise, active learning must be able to cope with noisy data. We show how it is possible to cope with even malicious noise in an active learning setting, removing noise an obstacle to regular application of active learning.

See Also:

Download slides icon Download slides: mlss06tw_langford_aal.pdf (1.1 MB)


Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Ken Dwyer, May 22, 2007 at 6:51 p.m.:

This lecture provides an excellent summary of the main ideas in the ICML paper:

http://www.icml2006.org/icml_document...

The paper points out some weaknesses and limitations of existing active learning methods, in particular, their inability to cope with arbitrary forms of noise. The proposed algorithm, called "Agnostic Active Learning" (or A-squared), makes no assumptions regarding the type of noise. The authors prove that an exponential reduction in the number of samples is indeed possible when the amount of noise is not too large. In the video, an example is presented of learning a threshold on the real line, which helps to illustrate the main concepts. Following the lecture, John fields a few questions, one of which is concerned with the tractability of A-squared when other hypothesis classes are considered; he concedes that there can be significant computational issues. From the paper: “Checking for disagreement amongst all remaining classifiers can be very computationally intensive.” Nevertheless, A-squared is an innovative idea that should be of interest to any student of active learning and/or learning theory.

Write your own review or comment:

make sure you have javascript enabled or clear this field: