Mixing of Stochastic Accelerated Gradient Descent

Zhang Peiyuan
Zhang Peiyuan
Daneshmand Hadi
Daneshmand Hadi
Cited by: 0|Views17

Abstract:

We study the mixing properties for stochastic accelerated gradient descent (SAGD) on least-squares regression. First, we show that stochastic gradient descent (SGD) and SAGD are simulating the same invariant distribution. Motivated by this, we then establish mixing rate for SAGD-iterates and compare it with those of SGD-iterates. Theore...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments