HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation

Understand

Stochastic gradient descent (SGD) is an immensely popular approach for online learning in settings where data arrives in a stream or data sizes are very large.

• However, despite an ever-increasing volume of work on SGD, much less is known about the statistical inferential properties of SGD-based predictions.
• Taking a fully inferential viewpoint, this paper introduces a novel procedure termed HiGrad to conduct statistical inference for online learning, without incurring additional computational cost compared with SGD.
• The HiGrad procedure begins by performing SGD updates for a while and then splits the single thread into several threads, and this procedure hierarchically operates in this fashion along each thread.