Parallelizing stochastic gradient descent for least squares regression
JainPrateek, NetrapalliPraneeth, M KakadeSham, KidambiRahul, SidfordAaron · Journal of Machine Learning Research · 2017
This work characterizes the benefits of averaging techniques widely used in conjunction with stochastic gradient descent (SGD). In particular, this work presents a sharp analysis of: (1) mini-batch...