all InfoSec news
High-Dimensional Private Empirical Risk Minimization by Greedy Coordinate Descent. (arXiv:2207.01560v2 [cs.LG] UPDATED)
Oct. 24, 2022, 1:20 a.m. | Paul Mangold, Aurélien Bellet, Joseph Salmon, Marc Tommasi
cs.CR updates on arXiv.org arxiv.org
In this paper, we study differentially private empirical risk minimization
(DP-ERM). It has been shown that the worst-case utility of DP-ERM reduces
polynomially as the dimension increases. This is a major obstacle to privately
learning large machine learning models. In high dimension, it is common for
some model's parameters to carry more information than others. To exploit this,
we propose a differentially private greedy coordinate descent (DP-GCD)
algorithm. At each iteration, DP-GCD privately performs a coordinate-wise
gradient step along the …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Lead Security Specialist
@ Fujifilm | Holly Springs, NC, United States
Security Operations Centre Analyst
@ Deliveroo | Hyderabad, India (Main Office)
CISOC Analyst
@ KCB Group | Kenya
Lead Security Engineer – Red Team/Offensive Security
@ FICO | Work from Home, United States
Cloud Security SME
@ Maveris | Washington, District of Columbia, United States - Remote
SOC Analyst (m/w/d)
@ Bausparkasse Schwäbisch Hall | Schwäbisch Hall, DE