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

by   Weijie Su, et al.

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. With predictions provided by multiple threads in place, a t-based confidence interval is constructed by decorrelating predictions using covariance structures given by the Ruppert--Polyak averaging scheme. Under certain regularity conditions, the HiGrad confidence interval is shown to attain asymptotically exact coverage probability. Finally, the performance of HiGrad is evaluated through extensive simulation studies and a real data example. An R package higrad has been developed to implement the method.



There are no comments yet.


page 22


On Scalable Inference with Stochastic Gradient Descent

In many applications involving large dataset or online updating, stochas...

Statistical inference using SGD

We present a novel method for frequentist statistical inference in M-est...

A Fully Online Approach for Covariance Matrices Estimation of Stochastic Gradient Descent Solutions

Stochastic gradient descent (SGD) algorithm is widely used for parameter...

Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling

We develop a new method of online inference for a vector of parameters e...

Online Statistical Inference for Parameters Estimation with Linear-Equality Constraints

Stochastic gradient descent (SGD) and projected stochastic gradient desc...

Towards stability and optimality in stochastic gradient descent

Iterative procedures for parameter estimation based on stochastic gradie...

Time-Smoothed Gradients for Online Forecasting

Here, we study different update rules in stochastic gradient descent (SG...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.