Statistical Inference for Stochastic Approximation and Online Learning via Hierarchical Incremental Gradient Descent
Neyman Seminar
Dec 6, 2017, 04:00 PM - 05:00 PM | 1011 Evans Hall | Happening As Scheduled
Weijie Su, University of Pennsylvania
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,...