all AI news
NanoBatch Privacy: Enabling fast Differentially Private learning on the IPU. (arXiv:2109.12191v2 [cs.LG] UPDATED)
June 6, 2022, 1:12 a.m. | Edward H. Lee, Mario Michael Krell, Alexander Tsyplikhin, Victoria Rege, Errol Colak, Kristen W. Yeom
cs.CV updates on arXiv.org arxiv.org
Differentially private SGD (DPSGD) has recently shown promise in deep
learning. However, compared to non-private SGD, the DPSGD algorithm places
computational overheads that can undo the benefit of batching in GPUs.
Micro-batching is a common method to alleviate this and is fully supported in
the TensorFlow Privacy library (TFDP). However, it degrades accuracy. We
propose NanoBatch Privacy, a lightweight add-on to TFDP to be used on Graphcore
IPUs by leveraging batch size of 1 (without microbatching) and gradient
accumulation. This …
More from arxiv.org / cs.CV updates on arXiv.org
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
1 day, 16 hours ago |
arxiv.org
Fingerprint Matching with Localized Deep Representation
1 day, 16 hours ago |
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
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne