Biography
I reveived my PhD in Mathematics from the University of Innsbruck, Austria, where I focused on numerical methods for time-dependent partial differential equations. During a post doc period at the University of Helsinki, I started research on privacy-preserving machine learning, in particular on differential privacy. I joined Nokia Bell Labs in December 2021 and my research interests are around deep learning methods and differential privacy.
I regularly review for conferences such as NeurIPS (top reviewer 2023), ICML, ICLR and AISTATS.
1 Articles found
- PhD, Mathematics, University of Innsbruck, Austria, 2014.
- MSc, Engineering Physics and Mathematics, Aalto University, Finland, 2010.
- Practical differentially private hyperparameter tuning with subsampling
A Koskela, T Kulkarni
Thirty-seventh Conference on Neural Information Processing Systems 2023 - Improving the privacy and practicality of objective perturbation for differentially private linear learners
R Redberg, A Koskela, YX Wang
Thirty-seventh Conference on Neural Information Processing Systems 2023 - Individual Privacy Accounting with Gaussian Differential Privacy
A Koskela, M Tobaben, A Honkela
International Conference on Learning Representations 2023 - Numerical Accounting in the Shuffle Model of Differential Privacy
A Koskela, M Heikkilä, A Honkela
Transactions on Machine Learning Research 2023
- Member of the ELLIS network (https://ellis.eu/members)
On this page
Biography
Blogs/Articles
Education
Selected Articles and Publications
Memberships