 |
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
|||||||||||
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
|
 |
 |
|
||||||||||
 |
|
|||||||||||
 |
|
|||||||||||
 |
 |
|
||||||||||
| Seminar Schedule (Seminar Organizer: Prof. Ziv Bar-Joseph) | |
Machine Learning Lunchtime Chats
|
Summer 2005 Seminar
Date: July 6, 2005 Time: 12:00 PM - 1:00 PM Location: 4623 Wean Hall Speaker: Alex Rojas-Pena CALD Masters Student Title: Conditional Density Estimation using Finite Mixture Models with an Application to Astrophysics Abstract: Conditional density estimation (CDE) is a statistical technique that allows for a better understanding of the relationship between a response variable and a set of covariates in comparison with usual regression methods. Therefore, this technique is of great importance to many scientific fields where knowledge about conditional means, obtained by regression methods, is not enough to draw valuable conclusions about the problem at hand. There is a variety of conditional density estimators, but most of them lack an ease of interpretation or generality. We present a solution to this problem by modeling the conditional density of $Y$ given $X$ using finite mixture models and estimating the parameter functions using local likelihood estimation. We use the proposed estimator to analyze the relationship between galaxy evolution and local density.