21 citations · 79 across the 19 of their papers we have counts for
6 papers · 1 filter
Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy
Di Wang, Marco Gaboardi, Adam Smith +1
In this paper, we study the Empirical Risk Minimization (ERM) problem in the non-interactive Local Differential Privacy (LDP) model. Previous research on this problem \citep{smith2…
On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data
Di Wang, Hanshen Xiao, Srini Devadas +1
In this paper, we consider the problem of designing Differentially Private (DP) algorithms for Stochastic Convex Optimization (SCO) on heavy-tailed data. The irregularity of such d…
Robust High Dimensional Expectation Maximization Algorithm via Trimmed Hard Thresholding
Di Wang, Xiangyu Guo, Shi Li +1
In this paper, we study the problem of estimating latent variable models with arbitrarily corrupted samples in high dimensional space ({\em i.e.,} ) where the underlying pa…
Estimating Stochastic Linear Combination of Non-linear Regressions Efficiently and Scalably
Di Wang, Xiangyu Guo, Chaowen Guan +2
Recently, many machine learning and statistical models such as non-linear regressions, the Single Index, Multi-index, Varying Coefficient Index Models and Two-layer Neural Networks…
Differentially Private (Gradient) Expectation Maximization Algorithm with Statistical Guarantees
Di Wang, Jiahao Ding, Lijie Hu +3
(Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. A major challenge facing th…
Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness
Tianhang Zheng, Di Wang, Baochun Li +1
As a certified defensive technique, randomized smoothing has received considerable attention due to its scalability to large datasets and neural networks. However, several importan…