all AI news
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints. (arXiv:2210.01864v1 [cs.LG])
Oct. 6, 2022, 1:11 a.m. | Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta
cs.LG updates on arXiv.org arxiv.org
All state-of-the-art (SOTA) differentially private machine learning (DP ML)
methods are iterative in nature, and their privacy analyses allow publicly
releasing the intermediate training checkpoints. However, DP ML benchmarks, and
even practical deployments, typically use only the final training checkpoint to
make predictions. In this work, for the first time, we comprehensively explore
various methods that aggregate intermediate checkpoints to improve the utility
of DP training. Empirically, we demonstrate that checkpoint aggregations
provide significant gains in the prediction accuracy over …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Sr. Software Development Manager, AWS Neuron Machine Learning Distributed Training
@ Amazon.com | Cupertino, California, USA