Title: Parameter Expanded Variational Bayesian Methods Yuan (Alan) Qi and Tommi S. Jaakkola, MIT NIPS 2006
1Parameter Expanded Variational Bayesian
MethodsYuan (Alan) Qi and Tommi S. Jaakkola,
MITNIPS 2006
- Presented by John Paisley
- Duke University, ECE
- 3/13/2009
2Outline
- Introduction
- PX-VB algorithm
- Applications
- Bayesian Probit Regression
- Automatic Relevance Determination
- Convergence Properties
- Conclusion
3Introduction
- Variational Bayes is a popular method for
approximating the posterior distribution of a
model. - Can be slow to converge if variables are strongly
correlated - Parameter-expanded methods can speed convergence
by adding auxiliary parameters, which can remove
the strong coupling of parameters.
4PX-VB algorithm
Auxiliary variables are added and optimized with
each iteration. The original parameters are then
recovered by setting the auxiliary variables to
the values that recover the original model.
5Bayesian Probit Regression
- The original model Where TN is the
truncated-Gaussian
- The parameter-expanded model
Where q(z_n) and q(w) updated with this
is followed by the inverse mapping
6Bayesian Probit Regression Results
7Automatic Relevance Determination (RVM)
- Separate auxiliary variables
As well as an auxiliary variable for \alpha, the
details for which are omitted
- Shared auxiliary variable
The auxiliary variable c is optimized with each
iteration using the iterative Newton method, as
no closed form solution exists.
8Automatic Relevance Determination Results
9Convergence Properties
- A general convergence theorem was presented and
proven
10Conclusion
- The theorem and proof shows that as long as the
inverse mapping function, M_a, has a largest
eigenvalue smaller than 1, PX-VB is guaranteed to
converge faster than VB, with the rate of
convergence increasing as this value decreases. - The approach presented was a general method for
speeding up VB inference. This was demonstrated
on two popular Bayesian models.