Statistics – Machine Learning
Scientific paper
2008-02-20
The 21st Annual Conference on Learning Theory (COLT 2008), Helsinki, Finland
Statistics
Machine Learning
12 pages, 3 figures, to appear in COLT 2008
Scientific paper
Undirected graphs are often used to describe high dimensional distributions. Under sparsity conditions, the graph can be estimated using $\ell_1$ penalization methods. However, current methods assume that the data are independent and identically distributed. If the distribution, and hence the graph, evolves over time then the data are not longer identically distributed. In this paper, we show how to estimate the sequence of graphs for non-identically distributed data, where the distribution evolves over time.
Lafferty John
Wasserman Larry
Zhou Shuheng
No associations
LandOfFree
Time Varying Undirected Graphs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Time Varying Undirected Graphs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Time Varying Undirected Graphs will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-578052