Timezone: »
Robust and Differentially Private Covariance Estimation
Logan Gnanapragasam · Jonathan Hayase · Sewoong Oh
In analyzing data from multiple participants, such as the US Census, the privacy of sensitive information should be protected and the analysis needs to be robust against malicious participants injecting corrupted data. To this end, we study a fundamental statistical problem of estimating the covariance from i.i.d. samples of a zero mean Gaussian distribution. We provide the first efficient algorithm that achieves both robustness and privacy. We provide statistical guarantees showing that we pay an extra factor d in the sample complexity, compared to the minimax optimal sample complexity.
Author Information
Logan Gnanapragasam
Jonathan Hayase (University of Washington)
Sewoong Oh (University of Washington)
More from the Same Authors
-
2021 Poster: Defense against backdoor attacks via robust covariance estimation »
Jonathan Hayase · Weihao Kong · Raghav Somani · Sewoong Oh -
2021 Spotlight: Defense against backdoor attacks via robust covariance estimation »
Jonathan Hayase · Weihao Kong · Raghav Somani · Sewoong Oh -
2019 Poster: Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms »
Ashok Vardhan Makkuva · Pramod Viswanath · Sreeram Kannan · Sewoong Oh -
2019 Oral: Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms »
Ashok Vardhan Makkuva · Pramod Viswanath · Sreeram Kannan · Sewoong Oh -
2019 Poster: Rate Distortion For Model Compression:From Theory To Practice »
Weihao Gao · Yu-Han Liu · Chong Wang · Sewoong Oh -
2019 Oral: Rate Distortion For Model Compression:From Theory To Practice »
Weihao Gao · Yu-Han Liu · Chong Wang · Sewoong Oh