Statistical Inference for Stochastic Approximation and Online Learning via Hierarchical Incremental Gradient Descent

Neyman Seminar
Dec 6, 2017 4:00pm to 5:00pm
Location: 
1011 Evans Hall
Status: 
Happening As Scheduled
Stochastic gradient descent (SGD) is an immensely popular approach for optimization in settings where data arrives in a stream or data sizes are very large. Despite an ever-increasing volume of works on SGD, less is known about statistical inferential properties of predictions based on SGD solutions. In this paper, we introduce a novel procedure termed HiGrad to conduct inference on predictions,...
Weijie Su, University of Pennsylvania