SampleRank: Training Factor Graphs with Atomic Gradients

Michael L. Wick, Khashayar Rohanimanesh, Kedar Bellare, Aron Culotta, Andrew McCallum

Abstract: We present SampleRank, an alternative to contrastive divergence (CD) for estimating parameters in complex graphical models. SampleRank 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).