Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Antti Koskela; Joonas Jalko; Lukas Prediger; Antti Honkela

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Antti Koskela, Joonas Jalko, Lukas Prediger, Antti Honkela

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Original language	English
Title of host publication	24th International Conference on Artificial Intelligence and Statistics (AISTATS)
Editors	A Banerjee, K Fukumizu
Number of pages	10
Publisher	Microtome Publishing
Publication date	2021
Publication status	Published - 2021
MoE publication type	A4 Article in conference proceedings
Event	24th International Conference on Artificial Intelligence and Statistics (AISTATS) - Duration: 13 Apr 2021 → 15 Apr 2021

Publication series

Name	Proceedings of Machine Learning Research
Publisher	MICROTOME PUBLISHING
Volume	130
ISSN (Print)	2640-3498

Fields of Science

113 Computer and information sciences

Access to Document

FFTFinal published version, 479 KBLicence: Unspecified

Cite this

@inproceedings{d06fca2c8b63453cb8829ce4ecf41cb4,

title = "Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT",

keywords = "113 Computer and information sciences",

author = "Antti Koskela and Joonas Jalko and Lukas Prediger and Antti Honkela",

year = "2021",

language = "English",

series = "Proceedings of Machine Learning Research",

publisher = "Microtome Publishing",

editor = "A Banerjee and K Fukumizu",

booktitle = "24th International Conference on Artificial Intelligence and Statistics (AISTATS)",

address = "United States",

note = "24th International Conference on Artificial Intelligence and Statistics (AISTATS) ; Conference date: 13-04-2021 Through 15-04-2021",

}

Koskela, A, Jalko, J, Prediger, L & Honkela, A 2021, Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT. in A Banerjee & K Fukumizu (eds), 24th International Conference on Artificial Intelligence and Statistics (AISTATS). Proceedings of Machine Learning Research, vol. 130, Microtome Publishing, 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 13/04/2021.

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT. / Koskela, Antti; Jalko, Joonas; Prediger, Lukas et al.
24th International Conference on Artificial Intelligence and Statistics (AISTATS). ed. / A Banerjee; K Fukumizu. Microtome Publishing, 2021. (Proceedings of Machine Learning Research; Vol. 130).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

AU - Koskela, Antti

AU - Jalko, Joonas

AU - Prediger, Lukas

AU - Honkela, Antti

PY - 2021

Y1 - 2021

KW - 113 Computer and information sciences

UR - https://proceedings.mlr.press/v130/

M3 - Conference contribution

T3 - Proceedings of Machine Learning Research

BT - 24th International Conference on Artificial Intelligence and Statistics (AISTATS)

A2 - Banerjee, A

A2 - Fukumizu, K

PB - Microtome Publishing

T2 - 24th International Conference on Artificial Intelligence and Statistics (AISTATS)

Y2 - 13 April 2021 through 15 April 2021

ER -

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

Publication series

Fields of Science

Access to Document

Other files and links

Cite this