Question: 13.1 Extension to Bregman divergences. (a) Show how conditional Maxent models can be extended by using arbitrary Bregman divergences instead of the (unnormalized) relative entropy.
13.1 Extension to Bregman divergences.
(a) Show how conditional Maxent models can be extended by using arbitrary Bregman divergences instead of the (unnormalized) relative entropy.
(b) Prove a duality theorem similar to Theorem 13.1 for theses extensions.
(c) Derive theoretical guarantees for these extensions. What additional property is needed for the Bregman divergence so that your learning guarantees hold?
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
