all InfoSec news
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
Feb. 27, 2024, 5:11 a.m. | Daniil Dmitriev, Krist\'of Szab\'o, Amartya Sanyal
cs.CR updates on arXiv.org arxiv.org
Abstract: In this paper, we provide lower bounds for Differentially Private (DP) Online Learning algorithms. Our result shows that, for a broad class of $(\varepsilon,\delta)$-DP online algorithms, for $T$ such that $\log T\leq O(1 / \delta)$, the expected number of mistakes incurred by the algorithm grows as $\Omega(\log \frac{T}{\delta})$. This matches the upper bound obtained by Golowich and Livni (2021) and is in contrast to non-private online learning where the number of mistakes is independent of …
algorithms arxiv class cs.cr cs.lg delta growth log mistakes online learning perspective private result
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
2 days, 11 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
2 days, 11 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
2 days, 11 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Network Security Engineer
@ Meta | Menlo Park, CA | Remote, US
Security Engineer, Investigations - i3
@ Meta | Washington, DC
Threat Investigator- Security Analyst
@ Meta | Menlo Park, CA | Seattle, WA | Washington, DC
Security Operations Engineer II
@ Microsoft | Redmond, Washington, United States
Engineering -- Tech Risk -- Global Cyber Defense & Intelligence -- Bug Bounty -- Associate -- Dallas
@ Goldman Sachs | Dallas, Texas, United States