Annealing Between Distributions by Averaging Moments
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Zoubin Ghahramani.
Many powerful Monte Carlo techniques for estimating partition functions, such as annealed importance sampling (AIS), are based on sampling from a sequence of intermediate distributions, which interpolate between a tractable initial distribution and an intractable target distribution. The nearuniversal practice is to use geometric averages of the initial and target distributions, but alternative paths can perform substantially better. We present a novel sequence of intermediate distributions for exponential families: averaging the moments of the initial and target distributions. We derive an asymptotically optimal piecewise linear schedule for the moments path and show that it performs at least as well as geometric averages with a linear schedule. Moment averaging performs well empirically at estimating partition functions of restricted Boltzmann machines (RBMs), which form the building blocks of many deep learning models.
This talk is part of the Machine Learning @ CUED series.
This talk is included in these lists:
Note that exdirectory lists are not shown.
