Andrea Bertazzi — accepted AI-conference papers

2025

Differential Privacy Guarantees of Markov Chain Monte Carlo Algorithms

Andrea Bertazzi, Tim Johnston, Gareth O. Roberts, Alain Oliviero Durmus

ICML 2025poster

This paper aims to provide differential privacy (DP) guarantees for Markov chain Monte Carlo (MCMC) algorithms. In a first part, we establish DP guarantees on samples output by MCMC algorithms as well as Monte Carlo estimators associated with these methods under assumptions on the convergence proper…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Piecewise deterministic generative models

Andrea Bertazzi, Dario Shariatian, Umut Simsekli, Eric Moulines, Alain Oliviero Durmus

NeurIPS 2024poster

We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), a family of non-diffusive stochastic processes consisting of deterministic motion and random jumps at random times. Similarly to diffusions, such Markov processes admit time reversals that turn…

Cited by 2 Source ↗PDF ↗Scholar ↗