Differentially Private Learning of Structured Discrete Distributions

By C. Cortes, N. Lawrence, Masashi Sugiyama, Roman Garnett. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Federated Heavy Hitters Discovery with Differential Privacy (2019, background): “…frequent sequence mining, and heavy-hitter discovery both in the central and local models of DP (Bhaskar et al., 2010; Bonomi and Xiong, 2013; Diakonikolas et al., 2015; Xu et al., 2016; Zhou and Lin, 2018; Kairouz et al., 2016; Wang et al., 2017; Bassily et al., 2017; Acharya et al., 2018;…”
Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communication (2018, background): “Sample privacy trade-oﬀs have been recently studied for various problems, including distribution estimation [23, 31, 47, 43, 20, 35].”
Differentially Private Testing of Identity and Closeness of Discrete Distributions (2017, background): “[DHS15] study structured distribution estimation under diﬀerential privacy.”
INSPECTRE: Privately Estimating the Unseen (2018, background): “In general, this is not true – for many other problems, including distribution estimation and hypothesis testing, the additional cost of privacy depends signiﬁcantly on the support size or dimension [DHS15, CDK17, ASZ17, ADR17].”
Two Party Distribution Testing: Communication and Security (2018, background): “While we are not aware of any work on secure testing, several recent papers address diﬀerentially-private distribution testing [DHS15, CDK17, ASZ17, ADR17].”