Kristjan Greenewald

Post-processing Private Synthetic Data for Improving Utility on Selected Measures

2023 · arXiv (Cornell University)

Existing private synthetic data generation algorithms are agnostic to downstream tasks. However, end users may have specific requirements that the synthetic data must satisfy. Failure to meet these requirements could significantly reduce the utility of …

𝑘-Variance: A Clustered Notion of Variance

2022 · DSpace@MIT (Massachusetts Institute of Technology)

We introduce 𝑘-variance, a generalization of variance built on the machinery of random bipartite matchings. 𝑘-variance measures the expected cost of matching two sets of 𝑘 samples from a distribution to each other, capturing local …