all InfoSec news
Differentially Private SGDA for Minimax Problems. (arXiv:2201.09046v3 [cs.LG] UPDATED)
April 28, 2022, 1:20 a.m. | Zhenhuan Yang, Shu Hu, Yunwen Lei, Kush R. Varshney, Siwei Lyu, Yiming Ying
cs.CR updates on arXiv.org arxiv.org
Stochastic gradient descent ascent (SGDA) and its variants have been the
workhorse for solving minimax problems. However, in contrast to the
well-studied stochastic gradient descent (SGD) with differential privacy (DP)
constraints, there is little work on understanding the generalization (utility)
of SGDA with DP constraints. In this paper, we use the algorithmic stability
approach to establish the generalization (utility) of DP-SGDA in different
settings. In particular, for the convex-concave setting, we prove that the
DP-SGDA can achieve an optimal utility …
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Transfer GMP Compliance Officer
@ Pharmathen | Sapes, East Macedonia and Thrace, Greece
Security Cyber Consultant DRC (m/w/d)
@ Atos | Berlin, DE, D-13353
Penetration Tester - InfoSec
@ Rapid7 | NIS Belfast
Cyber Vulnerability Lead
@ Under Armour | Remote, US