all AI news
Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples
April 24, 2024, 4:43 a.m. | Mohammad Afzali, Hassan Ashtiani, Christopher Liaw
cs.LG updates on arXiv.org arxiv.org
Abstract: We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP). Our main result is that $\text{poly}(k,d,1/\alpha,1/\varepsilon,\log(1/\delta))$ samples are sufficient to estimate a mixture of $k$ Gaussians in $\mathbb{R}^d$ up to total variation distance $\alpha$ while satisfying $(\varepsilon, \delta)$-DP. This is the first finite sample complexity upper bound for the problem that does not make any structural assumptions on the GMMs.
To solve the problem, we devise a new framework …
abstract alpha arxiv cs.cr cs.ds cs.it cs.lg delta differential differential privacy math.it polynomial privacy samples stat.ml study text total type variation
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US