all AI news
LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models
April 16, 2024, 4:43 a.m. | Juntaek Lim, Youngeun Kwon, Ranggi Hwang, Kiwan Maeng, G. Edward Suh, Minsoo Rhu
cs.LG updates on arXiv.org arxiv.org
Abstract: Differential privacy (DP) is widely being employed in the industry as a practical standard for privacy protection. While private training of computer vision or natural language processing applications has been studied extensively, the computational challenges of training of recommender systems (RecSys) with DP have not been explored. In this work, we first present our detailed characterization of private RecSys training using DP-SGD, root-causing its several performance bottlenecks. Specifically, we identify DP-SGD's noise sampling and noisy …
abstract algorithm applications arxiv challenges computational computer computer vision cs.cr cs.ir cs.lg designing differential differential privacy industry language language processing natural natural language natural language processing practical privacy processing protection recommendation recommender systems recsys scalable software standard systems training type vision
More from arxiv.org / cs.LG updates on 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
Business Data Scientist, gTech Ads
@ Google | Mexico City, CDMX, Mexico
Lead, Data Analytics Operations
@ Zocdoc | Pune, Maharashtra, India