Variational Bayes on Manifolds

Event status:

You are welcome to attend the following Statistics and Stochastic colloquium (part of the Colloquium Series of the Department of Mathematics and Statistics) at La Trobe University.

Thursday 17 June 2021 12:00 pm until Thursday 17 June 2021 01:00 pm (Add to calendar)
Andriy Olenko
Presented by:
A/Prof Minh-Ngoc Tran, University of Sydney
Type of Event:


Variational Bayes (VB) has become a widely-used tool for Bayesian inference in statistics and machine learning. Nonetheless, the development of the existing VB algorithms is so far generally restricted to the case where the variational parameter space is Euclidean, which hinders the potential broad application of VB methods. This paper extends the scope of VB to the case where the variational parameter space is a Riemannian manifold. We develop an efficient manifold-based VB algorithm that exploits both the geometric structure of the constraint parameter space and the information geometry of the manifold of VB approximating probability distributions. Our algorithm is provably convergent and achieves a decent convergence rate. We develop in particular several manifold VB algorithms including Manifold Gaussian VB and Stiefel Neural Network VB, and demonstrate through numerical experiments that the proposed algorithms are stable, less sensitive to initialization and compares favourably to existing VB methods. This is a joint work with Dang Nguyen and Duy Nguyen.




27th Sep 2021 11:52am

Advanced search

September Next Previous

  • Sun
  • Mon
  • Tue
  • Wed
  • Thu
  • Fri
  • Sat