activity
20182020
most citedDifferentially private cross-silo federated learning

22 citations · 22 across the 3 of their papers we have counts for

collaborators

5 papers

math.NA2020

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

Peter Kandolf, Antti Koskela, Samuel D. Relton +1

The Fréchet derivative of the matrix function plays an important role in many different applications, including condition number estimation and network analysis.…

cs.CR202022 cited

Differentially private cross-silo federated learning

Mikko A. Heikkilä, Antti Koskela, Kana Shimizu +2

Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recent…

math.NA2020

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

Antti Koskela, Samuel D. Relton

We consider linearizations of stochastic differential equations with additive noise using the Karhunen-Loève expansion. We obtain our linearizations by truncating the expansion and…

stat.ML2019

Computing Tight Differential Privacy Guarantees Using FFT

Antti Koskela, Joonas Jälkö, Antti Honkela

Differentially private (DP) machine learning has recently become popular. The privacy loss of DP algorithms is commonly reported using -DP. In this paper, we propo…

stat.ML2018

Learning Rate Adaptation for Federated and Differentially Private Learning

Antti Koskela, Antti Honkela

We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness com…