Differentially private learning of geometric concepts

Haim Kaplan; Yishay Mansour; Yossi Matias; Uri Stemmer

Differentially private learning of geometric concepts

Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer

Department of Computer Science

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

Abstract

We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex). Our algorithms achieve (α,β)-PAC learning and (ϵ,δ)-differential privacy using a sample of size O~(1αϵklogd), where the domain is [d]×[d] and k is the number of edges in the union of polygons.

Original language	English GB
Title of host publication	Proceedings of the 36th International Conference on Machine Learning, PMLR
Pages	3233-3241
Volume	97
State	Published - 2019

Cite this

@inproceedings{7905787510df4d33ad06d4a64f43e2bd,

title = "Differentially private learning of geometric concepts",

abstract = "We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex). Our algorithms achieve (α,β)-PAC learning and (ϵ,δ)-differential privacy using a sample of size O~(1αϵklogd), where the domain is [d]×[d] and k is the number of edges in the union of polygons. ",

author = "Haim Kaplan and Yishay Mansour and Yossi Matias and Uri Stemmer",

year = "2019",

language = "אנגלית",

volume = "97",

pages = "3233--3241",

booktitle = "Proceedings of the 36th International Conference on Machine Learning, PMLR",

}

TY - GEN

T1 - Differentially private learning of geometric concepts

AU - Kaplan, Haim

AU - Mansour, Yishay

AU - Matias, Yossi

AU - Stemmer, Uri

PY - 2019

Y1 - 2019

N2 - We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex). Our algorithms achieve (α,β)-PAC learning and (ϵ,δ)-differential privacy using a sample of size O~(1αϵklogd), where the domain is [d]×[d] and k is the number of edges in the union of polygons.

AB - We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex). Our algorithms achieve (α,β)-PAC learning and (ϵ,δ)-differential privacy using a sample of size O~(1αϵklogd), where the domain is [d]×[d] and k is the number of edges in the union of polygons.

M3 - פרסום בספר כנס

VL - 97

SP - 3233

EP - 3241

BT - Proceedings of the 36th International Conference on Machine Learning, PMLR

ER -