Differentially private inference via noisy optimization

EI seminar
ESE - Theil Building
Marco Avella Medina
Thursday 21 Mar 2024, 12:00 - 13:00
E Building
Campus Woudestein
Add to calendar
ESE - Theil Building
Chris Gorzeman

We propose a general optimization-based framework for computing differentially private M-estimators and a new method for constructing differentially private confidence regions. First, we show that robust statistics can be used in conjunction with noisy gradient descent or noisy Newton methods in order to obtain optimal private estimators with global linear or quadratic convergence, respectively. 

Joint work with Casey Bradshaw and Po-Ling Loh

We establish local and global convergence guarantees, under both local strong convexity and self-concordance, showing that our private estimators converge with high probability to a small neighborhood of the nonprivate M-estimators. Second, we tackle the problem of parametric inference by constructing differentially private estimators of the asymptotic variance of our private M-estimators. This naturally leads to approximate pivotal statistics for constructing confidence regions and conducting hypothesis testing. We demonstrate the effectiveness of a bias correction that leads to enhanced small-sample empirical performance in simulations.  


You can sign up for this seminar by sending an email to eb-secr@ese.eur.nl. The lunch will be provided (vegetarian option included).


See also

Saddlepoint techniques for the statistical analysis of time series

Davide La Vecchia (University of Geneva)
Spring in Rotterdam

The Anatomy of Machine Learning-Based Portfolio Performance

Christian Montes Schutte, Aarhus University
Christian Montes Schutte smiling at the camera
More information

Do you want to know more about the event? Contact the secretariat Econometrics at eb-secr@ese.eur.nl.

Compare @count study programme

  • @title

    • Duration: @duration
Compare study programmes