Skip to yearly menu bar Skip to main content


Poster

Rao-Blackwellized Stochastic Gradients for Discrete Distributions

Runjing Liu · Jeffrey Regier · Nilesh Tripuraneni · Michael Jordan · Jon McAuliffe

Pacific Ballroom #232

Keywords: [ Approximate Inference ] [ Bayesian Methods ]


Abstract:

We wish to compute the gradient of an expectation over a finite or countably infinite sample space having K ≤ ∞ categories. When K is indeed infinite, or finite but very large, the relevant summation is intractable. Accordingly, various stochastic gradient estimators have been proposed. In this paper, we describe a technique that can be applied to reduce the variance of any such estimator, without changing its bias—in particular, unbiasedness is retained. We show that our technique is an instance of Rao-Blackwellization, and we demonstrate the improvement it yields on a semi-supervised classification problem and a pixel attention task.

Live content is unavailable. Log in and register to view live content