[Colloquium] Machine Learning Reduction s Workshop 9/11, 9/12
Meridel Trimble
mtrimble at tti-c.org
Tue Sep 9 11:08:11 CDT 2003
What: Machine Learning Reductions Workshop
Where: TTI-C (1427 East 60th Street, Second Floor - Press Building)
When: All day Thursday, September 11th and Friday, September 12th, 2003
Schedule of talks: http://www.tti-c.org/workshop/schedule.html
Overview: Reductions are constructs allowing us to transfer theory, algorithms,
and expertise from one machine learning problem to another problem. From a
theoretical point of view, reductions are particularly interesting because it
appears that they often end up working well in practice. (and Risi notes: From
a practical point of view, reductions are particularly interesting because it
appears that they often end up working well in theory.)
Examples of practical reductions include:
1.Boosting (Strong classification with weak classification).
2.Error Correcting Output Codes (multiclass classification with binary
classification).
3.Various reductions of reinforcement learning to regression, classification,
etc...
4.Canonical reductions of classification to density estimation from statistics.
We are, of course, interested in reductions in a wider sense than just these
examples. Obvious questions to address are:
1.What empirical evidence do we have for and against reductions?
2.How can we differentiate between "good" reductions and "bad" reductions?
3.Can we understand the difficulty of learning problems by their placement in a
reduction hierarchy?
4.What is a mapping of available reductions?
5.What learning problems are unrelated by reduction?
6.What reductions are not possible?
A focused workshop involving those who have worked on reductions might be very
fruitful in addressing these questions and laying the groundwork for a coherent
direction of research.
Refreshments will be provided.
For more information, please go to:
http://www.tti-c.org/workshop/machine_learning_reductions.html
or e-mail Meridel: mtrimble at tti-c.org
Toyota Technological Institute at Chicago
More information about the Colloquium
mailing list