all InfoSec news
Differentially Private Coordinate Descent for Composite Empirical Risk Minimization. (arXiv:2110.11688v3 [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
Machine learning models can leak information about the data used to train
them. To mitigate this issue, Differentially Private (DP) variants of
optimization algorithms like Stochastic Gradient Descent (DP-SGD) have been
designed to trade-off utility for privacy in Empirical Risk Minimization (ERM)
problems. In this paper, we propose Differentially Private proximal Coordinate
Descent (DP-CD), a new method to solve composite DP-ERM problems. We derive
utility guarantees through a novel theoretical analysis of inexact coordinate
descent. Our results show that, thanks …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Security Operations Engineer
@ Nokia | India
Machine Learning DevSecOps Engineer
@ Ford Motor Company | Mexico City, MEX, Mexico
Cybersecurity Defense Analyst 2
@ IDEMIA | Casablanca, MA, 20270
Executive, IT Security
@ CIMB | Cambodia
Cloud Security Architect - Microsoft (m/w/d)
@ Bertelsmann | Gütersloh, NW, DE, 33333
Senior Consultant, Cybersecurity - SOC
@ NielsenIQ | Chennai, India