most citedNever Go Full Batch (in Stochastic Convex Optimization)

2 citations · 2 across the 1 of their papers we have counts for

collaborators

2 papers

math.OC2021★ 2 cited

Never Go Full Batch (in Stochastic Convex Optimization)

Idan Amir, Yair Carmon, Tomer Koren +1

We study the generalization performance of optimization algorithms for stochastic convex optimization: these are first-order methods that only access the exact…

cs.LG2021

SGD Generalizes Better Than GD (And Regularization Doesn't Help)

Idan Amir, Tomer Koren, Roi Livni

We give a new separation result between the generalization performance of stochastic gradient descent (SGD) and of full-batch gradient descent (GD) in the fundamental stochastic co…