PhD student / postdoc positions in Bayesian ML with privacy
Supervisor: Prof. Antti Honkela
We are interested in developing privacy-preserving Bayesian inference methods that allow performing consistent Bayesian inference under strong privacy guarantees from differential privacy (DP). Such methods are crucial for enabling the generation of noise-aware private synthetic data: anonymous data that enables consistent downstream statistical inference (cf. Räisä et al., AISTATS 2023) but provably protects data subject privacy.
The positions are connected to our work in the European Lighthouse on Secure and Safe AI (ELSA) as well as the Finnish Center for Artificial Intelligence (FCAI), where Prof. Honkela leads a research programme on privacy-preserving and secure AI.
Prior knowledge on Bayesian inference or Bayesian machine learning is a strong asset. Prior experience on (differential) privacy is an advantage but not required.
- Vibrant AI research community with strong links to leading researchers in Europe (e.g. ELLIS, ELSA)
- Access to very good computational resources, including #3 fastest supercomputer in the world, LUMI
- Very livable city, very easy to get by using English
How to apply:
Examples of our recent related papers:
Ossi Räisä, Joonas Jälkö, Samuel Kaski, and Antti Honkela. Noise-Aware Statistical Inference with Differentially Private Synthetic Data. In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023) (2023).
Joonas Jälkö, Eemil Lagerspetz, Jari Haukka, Sasu Tarkoma, Antti Honkela, and Samuel Kaski. Privacy-preserving data sharing via probabilistic modeling. Patterns 2(7):100271 (2021).
Tejas Kulkarni, Joonas Jälkö, Antti Koskela, Samuel Kaski, and Antti Honkela. Differentially Private Bayesian Inference for Generalized Linear Models. In Proceedings of the 38th International Conference on Machine Learning (ICML 2021) (2021).
Antti Koskela, Joonas Jälkö, Lukas Prediger, and Antti Honkela. Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021) (2021).