[PDF][PDF] SampleRank: Training Factor Graphs with Atomic Gradients.

ML Wick, K Rohanimanesh, K Bellare, A Culotta… - ICML, 2011 - academia.edu
ICML, 2011academia.edu
We present SampleRank, an alternative to contrastive divergence (CD) for estimating
parameters in complex graphical models. SampleR-ank harnesses a user-provided loss
function to distribute stochastic gradients across an MCMC chain. As a result, parameter
updates can be computed between arbitrary MCMC states. SampleRank is not only faster
than CD, but also achieves better accuracy in practice (up to 23% error reduction on noun-
phrase coreference).
Abstract
We present SampleRank, an alternative to contrastive divergence (CD) for estimating parameters in complex graphical models. SampleR-ank harnesses a user-provided loss function to distribute stochastic gradients across an MCMC chain. As a result, parameter updates can be computed between arbitrary MCMC states. SampleRank is not only faster than CD, but also achieves better accuracy in practice (up to 23% error reduction on noun-phrase coreference).
academia.edu
Showing the best result for this search. See all results