Nikita Kalinin

Institute of Science and Technology Austria.

prof_pic.jpeg

Greetings! I am Nikita Kalinin, a PhD student in the Institute of Science and Technology Austria (ISTA), fortunate to be under the supervision of Christoph Lampert. I am exploring the intriguing field of Differential Privacy as part of my recent academic journey. I am particularly interested in the following topics:

  • Matrix Factorization Mechanism in Differential Privacy
  • Differentially Private Model Training
  • Differentially Private Parameter Estimation

selected publications

  1. AISTATS
    Efficient Estimation of a Gaussian Mean with Local Differential Privacy
    Nikita Kalinin ,  and  Lukas Steinberger
    Artificial Intelligence and Statistics (AISTATS) 2025, Feb 2024
  2. NeurIPS
    Banded square root matrix factorization for differentially private model training
    Kalinin Nikita ,  and  Lampert Christoph
    Advances in Neural Information Processing Systems (NeurIPS) 2024, Dec 2024
  3. arXiv
    Continual release moment estimation with differential privacy
    Nikita P Kalinin ,  Jalaj Upadhyay ,  and  Christoph H Lampert
    arXiv, Jun 2025
  4. arXiv
    Back to square roots: An optimal bound on the matrix factorization error for multi-epoch differentially private SGD
    Nikita P Kalinin ,  Ryan McKenna ,  Jalaj Upadhyay , and 1 more author
    arXiv, May 2025