On the Equivalence between Herding and Conditional Gradient Algorithms

Details On the Equivalence between Herding and Conditional Gradient Algorithms On the Equivalence between Herding and Conditional Gradient Algorithms

2012-03-20

arxiv.org/abs/1203.4523v1

Computer Science

Learning

Scientific paper

We show that the herding procedure of Welling (2009) takes exactly the form of a standard convex optimization algorithm--namely a conditional gradient algorithm minimizing a quadratic moment discrepancy. This link enables us to invoke convergence results from convex optimization and to consider faster alternatives for the task of approximating integrals in a reproducing kernel Hilbert space. We study the behavior of the different variants through numerical simulations. The experiments indicate that while we can improve over herding on the task of approximating integrals, the original herding algorithm tends to approach more often the maximum entropy distribution, shedding more light on the learning bias behind herding.

Affiliated with

Also associated with

No associations

Rating

On the Equivalence between Herding and Conditional Gradient Algorithms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with On the Equivalence between Herding and Conditional Gradient Algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On the Equivalence between Herding and Conditional Gradient Algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-496605