t-divergence Based Approximate Inference

Approximate inference is an important technique for dealing with large, intractable graphical models based on the exponential family of distributions. We extend the idea of approximate inference to the t-exponential family by defining a new t-divergence. This divergence measure is obtained via convex duality between the log-partition function of the t-exponential family and a new t-entropy. We illustrate our approach on the Bayes Point Machine with a Student's t-prior.

Authors

• Nan Ding Dalian University of Technology
• Yuan Qi Fudan University Shanghai Academy of Artificial Intelligence for Science
• S. V. N. Vishwanathan

Keywords

No keywords are indexed for this paper.