paper-with-me

Papers

Approximation Based Variance Reduction for Reparameterization Gradients

2020-07-29 · NeurIPS 2020 12 · Tomas Geffner, Justin Domke

Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance matrix, e.g. Gaussians with any covariance structure. The control variate is based on a quadratic approximation of the model, and its parameters are set using a double-descent scheme by minimizing the gradient estimator's variance. We empirically show that this control variate leads to large improvements in gradient variance and optimization convergence for inference with non-factorized variational distributions.

📄 PDF Abstract BibTeX arXiv:2007.14634

Code (1)

tomsons22/ABVRR pytorch

Tasks

Variational Inference

Similar Papers 제목 키워드 기반

Reducing Reparameterization Gradient Variance

2017-05-22 · NeurIPS 2017 12 · Andrew C. Miller, Nicholas J. Foti, Alexander D'Amour, Ryan P. Adams

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy grad…

Variational Inference

The Generalized Reparameterization Gradient

2016-10-07 · NeurIPS 2016 · Francisco J. R. Ruiz, Michalis K. Titsias, David M. Blei

The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as …

Variational Inference

The Generalized Reparameterization Gradient

2016-12-01 · NeurIPS 2016 12 · Francisco R. Ruiz, Michalis Titsias Rc Aueb, David Blei

The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as …

Variational Inference

Variational Inference with Numerical Derivatives: variance reduction through coupling

2019-06-17 · Alexander Immer, Guillaume P. Dehaene

The Black Box Variational Inference (Ranganath et al. (2014)) algorithm provides a universal method for Variational Inference, but taking advantage of special properties of the approximation family or of the target can i…

Variational Inference

Variance reduction properties of the reparameterization trick

2018-09-27 · Ming Xu, Matias Quiroz, Robert Kohn, Scott A. Sisson

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Althou…

Variational Inference