Approximate inference via variational sampling

Details Approximate inference via variational sampling Approximate inference via variational sampling

2011-05-08

arxiv.org/abs/1105.1508v2

Statistics

Computation

Working paper, 11 pages

Scientific paper

We propose a new method to approximately integrate a function with respect to a given probability distribution when an exact computation is intractable. The method is called "variational sampling" as it involves fitting a simplified distribution for which the integral has a closed-form expression, and using a set of randomly sampled control points to optimize the fit. The novelty lies in the chosen objective function, namely a Monte Carlo approximation to the generalized Kullback-Leibler divergence, which differs from classical methods that implement a similar idea, such as Bayesian Monte Carlo and importance sampling. We review several attractive mathematical properties of variational sampling, including well-posedness under a simple condition on the sample size, and a central limit theorem analogous to the case of importance sampling. We then report various simulations that essentially show that variational sampling has the potential to outperform existing methods within comparable computation time in estimating moments of order up to 2. We conclude with a brief discussion of desirable enhancements.

Affiliated with

Also associated with

No associations

Rating

Approximate inference via variational sampling 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 Approximate inference via variational sampling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Approximate inference via variational sampling will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-145074