Abstract Details
|
Activity Number:
|
209
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 4, 2014 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
|
Abstract #310726
|
|
|
Title:
|
Hamiltonian Monte Carlo: Are We There Yet?
|
|
Author(s):
|
Christof Seiler*+ and Susan Holmes and Simon Rubinstein-Salzedo
|
|
Companies:
|
Stanford University and Stanford University and Stanford University
|
|
Keywords:
|
Hamiltonian Monte Carlo ;
Riemannian geometry ;
Error estimates
|
|
Abstract:
|
When kids ask "Are we there yet?" in the car, parents usually have a pretty good estimate. When statisticians ask, a good estimate is very hard. In statistics the question is: How many more samples are needed to be close enough to a probability distribution?
In this talk, we formulate this timely question in the language of Riemannian geometry. Surprisingly, links between classical physics and statistics lead us to find new error estimates for Hamiltonian Monte Carlo in high-dimensions.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.