TY - GEN
T1 - Principal component analysis in the local differential privacy model
AU - Wang, Di
AU - Xu, Jinhui
N1 - Publisher Copyright:
© 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.
PY - 2019
Y1 - 2019
N2 - In this paper, we study the Principal Component Analysis (PCA) problem under the (distributed) non-interactive local differential privacy model. For the low dimensional case, we show the optimal ratefor the private minimax risk of the k-dimensional PCA using the squared subspace distance as the measurement. For the high dimensional row sparse case, we first give a lower bound on the private minimax risk, . Then we provide an efficient algorithm to achieve a near optimal upper bound. Experiments on both synthetic and real world datasets confirm the theoretical guarantees of our algorithms.
AB - In this paper, we study the Principal Component Analysis (PCA) problem under the (distributed) non-interactive local differential privacy model. For the low dimensional case, we show the optimal ratefor the private minimax risk of the k-dimensional PCA using the squared subspace distance as the measurement. For the high dimensional row sparse case, we first give a lower bound on the private minimax risk, . Then we provide an efficient algorithm to achieve a near optimal upper bound. Experiments on both synthetic and real world datasets confirm the theoretical guarantees of our algorithms.
UR - https://www.scopus.com/pages/publications/85074946981
U2 - 10.24963/ijcai.2019/666
DO - 10.24963/ijcai.2019/666
M3 - Conference contribution
AN - SCOPUS:85074946981
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 4795
EP - 4801
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
Y2 - 10 August 2019 through 16 August 2019
ER -