Web: http://arxiv.org/abs/2201.09046

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 …

lg problems

Senior Product Security Engineer

@ Panther Labs | United States

Lead, DevSecOps

@ Hex Trust | Singapore, Singapore, Singapore

Information Security GRC Lead

@ Bud | London, England, United Kingdom

Security Analyst

@ AnaVation | Quantico, VA

Security Engineer

@ Homebase | Atlanta, Georgia, United States

Principal Offensive Cloud Security Engineer

@ Uptycs | Remote, USA

Security Engineer

@ AnaVation | Quantico, VA

Information Systems Security Manager

@ Barbaricum | Washington, DC

Cloud Engineer - GCP Security Specialist

@ DoiT International | Remote Israel

Security Operations Analyst - Compliance

@ Algolia | London, England

GRC Lead - Software Compliance

@ Ivanti | United States

Security Administrator

@ Trusting Social | Ho Chi Minh City, Ho Chi Minh City, Vietnam