Skip to main content.
Advanced search >

<< December 2017 >>

Wednesday, December 6, 2017

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

Seminar: Neyman Seminar | December 6 | 4-5 p.m. | 1011 Evans Hall

Weijie Su, University of Pennsylvania

Department of Statistics

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,...   More >