315 citations · 790 across the 31 of their papers we have counts for
Showing 2018Show all
3 papers · 1 filter
math.OC2018★ 55 cited
On exponential convergence of SGD in non-convex over-parametrized learning
Raef Bassily, Mikhail Belkin, Siyuan Ma
Large over-parametrized models learned via stochastic gradient descent (SGD) methods have become a key element in modern machine learning. Although SGD methods are very effective i…
cs.LG2018★ 25 cited
Linear Queries Estimation with Local Differential Privacy
Raef Bassily
We study the problem of estimating a set of linear queries with respect to some unknown distribution over a domain based on a sensitive data set…
cs.LG2018★ 6 cited
Model-Agnostic Private Learning via Stability
Raef Bassily, Om Thakkar, Abhradeep Thakurta
We design differentially private learning algorithms that are agnostic to the learning model. Our algorithms are interactive in nature, i.e., instead of outputting a model based on…