all AI news
When Does Differentially Private Learning Not Suffer in High Dimensions?. (arXiv:2207.00160v3 [cs.LG] UPDATED)
Aug. 16, 2022, 1:12 a.m. | Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, Abhradeep Guha Thakurta
stat.ML updates on arXiv.org arxiv.org
Large pretrained models can be privately fine-tuned to achieve performance
approaching that of non-private models. A common theme in these results is the
surprising observation that high-dimensional models can achieve favorable
privacy-utility trade-offs. This seemingly contradicts known results on the
model-size dependence of differentially private convex learning and raises the
following research question: When does the performance of differentially
private learning not degrade with increasing model size? We identify that the
magnitudes of gradients projected onto subspaces is a key …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Enterprise Data Architect
@ Pathward | Remote
Diagnostic Imaging Information Systems (DIIS) Technologist
@ Nova Scotia Health Authority | Halifax, NS, CA, B3K 6R8
Intern Data Scientist - Residual Value Risk Management (f/m/d)
@ BMW Group | Munich, DE
Analytics Engineering Manager
@ PlayStation Global | United Kingdom, London
Junior Insight Analyst (PR&Comms)
@ Signal AI | Lisbon, Lisbon, Portugal