A Framework for Private Matrix Analysis in Sliding Window Model
Abstract
We perform a rigorous study of private matrix analysis when only the last $W$ updates to matrices are considered useful for analysis. We show the existing framework in the non-private setting is not robust to noise required for privacy. We then propose a framework robust to noise and use it to give first efficient $o(W)$ space differentially private algorithms for spectral approximation, principal component analysis (PCA), multi-response linear regression, sparse PCA, and non-negative PCA. Prior to our work, no such result was known for sparse and non-negative differentially private PCA even in the static data setting. We also give a lower bound to demonstrate the cost of privacy in the sliding window model.
Cite
Text
Upadhyay and Upadhyay. "A Framework for Private Matrix Analysis in Sliding Window Model." International Conference on Machine Learning, 2021.Markdown
[Upadhyay and Upadhyay. "A Framework for Private Matrix Analysis in Sliding Window Model." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/upadhyay2021icml-framework/)BibTeX
@inproceedings{upadhyay2021icml-framework,
title = {{A Framework for Private Matrix Analysis in Sliding Window Model}},
author = {Upadhyay, Jalaj and Upadhyay, Sarvagya},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {10465-10475},
volume = {139},
url = {https://mlanthology.org/icml/2021/upadhyay2021icml-framework/}
}