Antti Koskela

According to our database, Antti Koskela authored at least 28 papers between 2013 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Communication Efficient Differentially Private Federated Learning Using Second Order Information.

Mounssif Krouka, Antti Koskela, Tejas D. Kulkarni

Proc. Priv. Enhancing Technol., 2025

2024

Protecting Confidentiality, Privacy and Integrity in Collaborative Learning.

Dong Chen, Alice Dethise, Istemi Ekin Akkus, Ivica Rimac, Klaus Satzke, Antti Koskela, Marco Canini, Wei Wang, Ruichuan Chen

CoRR, 2024

Differentially Private Convex Approximation of Two-Layer ReLU Networks.

Antti Koskela

CoRR, 2024

Black Box Differential Privacy Auditing Using Total Variation Distance.

Antti Koskela, Jafar Mohammadi

CoRR, 2024

Privacy Profiles for Private Selection.

Antti Koskela, Rachel Redberg, Yu-Xiang Wang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Numerical Accounting in the Shuffle Model of Differential Privacy.

Antti Koskela, Mikko A. Heikkilä, Antti Honkela

Trans. Mach. Learn. Res., 2023

Practical Differentially Private Hyperparameter Tuning with Subsampling.

Antti Koskela, Tejas Kulkarni

CoRR, 2023

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners.

Rachel Redberg, Antti Koskela, Yu-Xiang Wang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Practical Differentially Private Hyperparameter Tuning with Subsampling.

Antti Koskela, Tejas D. Kulkarni

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Individual Privacy Accounting with Gaussian Differential Privacy.

Antti Koskela, Marlon Tobaben, Antti Honkela

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2021

Computing low-rank approximations of the Fréchet derivative of a matrix function using Krylov subspace methods.

Peter Kandolf, Antti Koskela, Samuel D. Relton, Marcel Schweitzer

Numer. Linear Algebra Appl., 2021

Differentially Private Hamiltonian Monte Carlo.

Ossi Räisä, Antti Koskela, Antti Honkela

CoRR, 2021

Tight Accounting in the Shuffle Model of Differential Privacy.

Antti Koskela, Mikko A. Heikkilä, Antti Honkela

CoRR, 2021

Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT.

Antti Koskela, Antti Honkela

CoRR, 2021

Differentially Private Bayesian Inference for Generalized Linear Models.

Tejas Kulkarni, Joonas Jälkö, Antti Koskela, Samuel Kaski, Antti Honkela

Proceedings of the 38th International Conference on Machine Learning, 2021

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT.

Antti Koskela, Joonas Jälkö, Lukas Prediger, Antti Honkela

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Differentially private cross-silo federated learning.

Mikko A. Heikkilä, Antti Koskela, Kana Shimizu, Samuel Kaski, Antti Honkela

CoRR, 2020

Tight Approximate Differential Privacy for Discrete-Valued Mechanisms Using FFT.

Antti Koskela, Joonas Jälkö, Lukas Prediger, Antti Honkela

CoRR, 2020

Sampling of Stochastic Differential Equations using the Karhunen-Loève Expansion and Matrix Functions.

Antti Koskela, Samuel D. Relton

CoRR, 2020

Computing Tight Differential Privacy Guarantees Using FFT.

Antti Koskela, Joonas Jälkö, Antti Honkela

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Learning Rate Adaptation for Differentially Private Learning.

Antti Koskela, Antti Honkela

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Computing Exact Guarantees for Differential Privacy.

Antti Koskela, Joonas Jälkö, Antti Honkela

CoRR, 2019

2018

Disguised and new quasi-Newton methods for nonlinear eigenvalue problems.

Elias Jarlebring, Antti Koskela, Giampaolo Mele

Numer. Algorithms, 2018

Learning rate adaptation for differentially private stochastic gradient descent.

Antti Koskela, Antti Honkela

CoRR, 2018

2016

Krylov Approximation of Linear ODEs with Polynomial Parameterization.

Antti Koskela, Elias Jarlebring, Michiel E. Hochstenbach

SIAM J. Matrix Anal. Appl., 2016

2014

A Moment-Matching Arnoldi Iteration for Linear Combinations of φ Functions.

Antti Koskela, Alexander Ostermann

SIAM J. Matrix Anal. Appl., 2014

2013

Exponential Taylor methods: Analysis and implementation.

Antti Koskela, Alexander Ostermann

Comput. Math. Appl., 2013

Approximating the Matrix Exponential of an Advection-Diffusion Operator Using the Incomplete Orthogonalization Method.

Antti Koskela

Proceedings of the Numerical Mathematics and Advanced Applications - ENUMATH 2013, 2013