AI Heap
Published on

Continual Release Moment Estimation with Differential Privacy

arXiv:2502.06597 - [arXiv,PDF]
Authors
  • Name
    Nikita P. Kalinin
  • Name
    Jalaj Upadhyay
  • Name
    Christoph H. Lampert
  • Affiliation
    Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria
  • Affiliation
    Department of Computer Science, Rutgers University, Piscataway, NJ 08854, USA
We propose Joint Moment Estimation (JME), a method for continually and privately estimating both the first and second moments of data with reduced noise compared to naive approaches. JME uses the matrix mechanism and a joint sensitivity analysis to allow the second moment estimation with no additional privacy cost, thereby improving accuracy while maintaining privacy. We demonstrate JME’s effectiveness in two applications: estimating the running mean and covariance matrix for Gaussian density estimation, and model training with DP-Adam on CIFAR-10.