← Search

Nicholas Foti

2 accepted papers

2017

Reducing Reparameterization Gradient Variance

NeurIPS 2017poster

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 gradients often used in Monte Carlo variational inference (MCVI). However, when th…

2015

Streaming Variational Inference for Bayesian Nonparametric Mixture Models

AISTATS 2015poster

In theory, Bayesian nonparametric (BNP) models are well suited to streaming data scenarios due to their ability to adapt model complexity based on the amount of data observed. Unfortunately, such benefits have not been fully realized in practice; existing inference algorithms either are not applicab…

Cited by 39SourcePDFScholar