Timezone: »

A Framework for Private Matrix Analysis in Sliding Window Model
Jalaj Upadhyay · Sarvagya Upadhyay

Thu Jul 22 07:30 PM -- 07:35 PM (PDT) @ None
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.

Author Information

Jalaj Upadhyay (Apple)
Sarvagya Upadhyay (Fujitsu Research America)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors