Private and Online Learnability Are Equivalent
Private and Online Learnability Are Equivalent
复制标题
私人学习和在线学习能力是等效的
DOI:
10.1145/3526074
复制
发表时间:
2022
影响因子:
2.5
通讯作者:
Moran, Shay
中科院分区:
文献类型:
--
作者:
Alon, Noga;Bun, Mark;Livni, Roi;Malliaris, Maryanthe;Moran, Shay
LetHbe a binary-labeled concept class. We prove thatHcan be PAC learned by an (approximate) differentially private algorithm if and only if it has a finite Littlestone dimension. This implies a qualitative equivalence between online learnability and private PAC learnability.
登录
查看更多内容
DOI:
--
发表时间:
2021
期刊:
Neural Information Processing Systems
影响因子:
--
作者:
Noah Golowich;Roi Livni
通讯作者:
Roi Livni
DOI:
--
发表时间:
2019
期刊:
Neural Information Processing Systems
影响因子:
--
作者:
Alon Cohen;Avinatan Hassidim;Haim Kaplan;Y. Mansour;S. Moran
通讯作者:
S. Moran
DOI:
--
发表时间:
2019
期刊:
影响因子:
--
作者:
T. Democracy;Cathy O’Neil;Harris Mateen
通讯作者:
Harris Mateen
DOI:
--
发表时间:
2014
期刊:
SIAM journal on computing (Print)
影响因子:
--
作者:
V. Feldman;David Xiao
通讯作者:
David Xiao
DOI:
10.1145/3188745.3188946
发表时间:
2018-06
期刊:
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing
影响因子:
--
作者:
Mark Bun;C. Dwork;G. Rothblum;T. Steinke
通讯作者:
Mark Bun;C. Dwork;G. Rothblum;T. Steinke