Publications

Our publications. More publications can be found from Google Scholar profiles of group members.
Selected publications

O Räisä, J Jälkö, A Honkela.
Subsampling is not magic: Why large batch sizes work for differentially private stochastic optimisation.
In Proceedings of the 41st International Conference on Machine Learning (ICML 2024) (2024).

M Tobaben, A Shysheya, JF Bronskill, A Paverd, S Tople, S Zanella-Beguelin, RE Turner, A Honkela.
On the Efficacy of Differentially Private Few-shot Image Classification.
Transactions on Machine Learning Research (2023).

A Koskela, MA Heikkilä, A Honkela.
Numerical Accounting in the Shuffle Model of Differential Privacy.
Transactions on Machine Learning Research (2023). (Featured paper.)

O Räisä, J Jälkö, S Kaski, A 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).

A Koskela, M Tobaben, A Honkela.
Individual Privacy Accounting with Gaussian Differential Privacy.
In Proceedings of the 11th International Conference on Learning Representations (ICLR 2023) (2023).

T Mäklin, HA Thorpe, AK Pöntinen, RA Gladstone, Y Shao, M Pesonen, A McNally, PJ Johnsen, Ø Samuelsen, TD Lawley, A Honkela, J Corander.
Strong pathogen competition in neonatal gut colonisation.
Nature Communications 13(1):7417 (2022).

T Mäklin, T Kallonen, J Alanko, Ø Samuelsen, K Hegstad, V Mäkinen, J Corander, E Heinz, and A Honkela.
Bacterial Genomic Epidemiology with Mixed Samples.
Microbial Genomics 7(11):000691 (2021).

J Jälkö, E Lagerspetz, J Haukka, S Tarkoma, A Honkela, and S Kaski.
Privacy-preserving data sharing via probabilistic modeling.
Patterns 2(7):100271 (2021).

T Kulkarni, J Jälkö, A Koskela, S Kaski, and A Honkela.
Differentially Private Bayesian Inference for Generalized Linear Models.
In Proceedings of the 38th International Conference on Machine Learning (ICML 2021) (2021).

A Koskela, J Jälkö, L Prediger, and A 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).

A Koskela, J Jälkö, and A Honkela.
Computing Tight Differential Privacy Guarantees Using FFT.
In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020) (2020).

MA Heikkilä, J Jälkö, O Dikmen, and A Honkela.
Differentially Private Markov Chain Monte Carlo.
In Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (2019).

T Niinimäki, M Heikkilä, A Honkela, and S Kaski.
Representation transfer for differentially private drug sensitivity prediction.
Bioinformatics 35(14):i218-i224 (2019).

A Honkela, M Das, A Nieminen, O Dikmen, and S Kaski.
Efficient differentially private learning improves drug sensitivity prediction.
Biology Direct 13(1):1 (2018).

M Heikkilä, E Lagerspetz, S Kaski, K Shimizu, S Tarkoma and A Honkela.
Differentially Private Bayesian Learning on Distributed Data.
In Advances in Neural Information Processing Systems 30 (NIPS 2017) (2017).

All publications (from the University database)