no code implementations • 24 Oct 2023 • Daniel M. Kane, Ilias Diakonikolas, Hanshen Xiao, Sihan Liu
We note that if the algorithm is allowed to wait until time $T$ to report its estimate, this reduces to the well-studied problem of robust mean estimation.
no code implementations • 7 Oct 2022 • Hanshen Xiao, Jun Wan, Srinivas Devadas
We also introduce a refined gradient clipping method, which can further sharpen the privacy loss in private learning when combined with ModelMix.
no code implementations • 23 Jul 2021 • Lijie Hu, Shuo Ni, Hanshen Xiao, Di Wang
To better understand the challenges arising from irregular data distribution, in this paper we provide the first study on the problem of DP-SCO with heavy-tailed data in the high dimensional space.
no code implementations • ICML 2020 • Di Wang, Hanshen Xiao, Srini Devadas, Jinhui Xu
For this case, we propose a method based on the sample-and-aggregate framework, which has an excess population risk of $\tilde{O}(\frac{d^3}{n\epsilon^4})$ (after omitting other factors), where $n$ is the sample size and $d$ is the dimensionality of the data.
no code implementations • 16 Feb 2019 • Hanshen Xiao, Yu Ye, Srinivas Devadas
Privacy concerns with sensitive data are receiving increasing attention.
no code implementations • 28 Nov 2018 • Nan Du, Zhikang Wang, Hanshen Xiao
Generalized Chinese Remainder Theorem (CRT) has been shown to be a powerful approach to solve the ambiguity resolution problem.