Timezone: »

t-divergence Based Approximate Inference
Nan Ding · S.V.N. Vishwanathan · Yuan Qi

Wed Dec 14 08:45 AM -- 02:59 PM (PST) @

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.

Author Information

Nan Ding (Google)
S.V.N. Vishwanathan (UCSC)
Yuan Qi (Purdue university)

More from the Same Authors