1.6k citations · 1.7k across the 22 of their papers we have counts for
8 papers · 1 filter
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping
Jiyan He, Xuechen Li, Da Yu +6
Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the tw…
Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
Janardhan Kulkarni, Yin Tat Lee, Daogao Liu
We study the differentially private Empirical Risk Minimization (ERM) and Stochastic Convex Optimization (SCO) problems for non-smooth convex functions. We get a (nearly) optimal b…
Fast and Memory Efficient Differentially Private-SGD via JL Projections
Zhiqi Bu, Sivakanth Gopi, Janardhan Kulkarni +3
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requ…
Composite Logconcave Sampling with a Restricted Gaussian Oracle
Ruoqi Shen, Kevin Tian, Yin Tat Lee
We consider sampling from composite densities on of the form for well-conditioned and convex (but possibly non-smooth) ,…
Network size and weights size for memorization with two-layers neural networks
Sébastien Bubeck, Ronen Eldan, Yin Tat Lee +1
In 1988, Eric B. Baum showed that two-layers neural networks with threshold activation function can perfectly memorize the binary labels of points in general position in $\math…
Logsmooth Gradient Concentration and Tighter Runtimes for Metropolized Hamiltonian Monte Carlo
Yin Tat Lee, Ruoqi Shen, Kevin Tian
We show that the gradient norm for , where is strongly convex and smooth, concentrates tightly around its mean. This removes a barrier in…