all AI news
Dynamic Privacy Budget Allocation Improves Data Efficiency of Differentially Private Gradient Descent. (arXiv:2101.07413v3 [cs.LG] UPDATED)
Oct. 20, 2022, 1:12 a.m. | Junyuan Hong, Zhangyang Wang, Jiayu Zhou
cs.LG updates on arXiv.org arxiv.org
Protecting privacy in learning while maintaining the model performance has
become increasingly critical in many applications that involve sensitive data.
Private Gradient Descent (PGD) is a commonly used private learning framework,
which noises gradients based on the Differential Privacy protocol. Recent
studies show that \emph{dynamic privacy schedules} of decreasing noise
magnitudes can improve loss at the final iteration, and yet theoretical
understandings of the effectiveness of such schedules and their connections to
optimization algorithms remain limited. In this paper, we …
More from arxiv.org / cs.LG updates on arXiv.org
A Single-Loop Algorithm for Decentralized Bilevel Optimization
1 day, 2 hours ago |
arxiv.org
CLEANing Cygnus A deep and fast with R2D2
1 day, 2 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Stagista Technical Data Engineer
@ Hager Group | BRESCIA, IT
Data Analytics - SAS, SQL - Associate
@ JPMorgan Chase & Co. | Mumbai, Maharashtra, India