Differentially Private Block Coordinate Descent for Linear Regression on Vertically Partitioned Data

Autor: Jins de Jong, Bart Kamphorst, Shannon Kroes

Publikováno v: Journal of Cybersecurity and Privacy, Vol 2, Iss 4, Pp 862-881 (2022)

We present a differentially private extension of the block coordinate descent algorithm by means of objective perturbation. The algorithm iteratively performs linear regression in a federated setting on vertically partitioned data. In addition to a p

Externí odkaz: https://doaj.org/article/46b1b90af222476d99bc0514c29f579a

Privacy-preserving dataset combination and Lasso regression for healthcare predictions

Autor: Marie Beth van Egmond, Gabriele Spini, Onno van der Galien, Arne IJpma, Thijs Veugen, Wessel Kraaij, Alex Sangers, Thomas Rooijakkers, Peter Langenkamp, Bart Kamphorst, Natasja van de L’Isle, Milena Kooij-Janic

Publikováno v: BMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-16 (2021)

Abstract Background Recent developments in machine learning have shown its potential impact for clinical use such as risk prediction, prognosis, and treatment selection. However, relevant data are often scattered across different stakeholders and the

Externí odkaz: https://doaj.org/article/8b263a8d1f5744b1a5839a1725efb851

Heavy-traffic analysis of sojourn time under the foreground–background scheduling policy

Autor: Bart Kamphorst, Bert Zwart

Publikováno v: Stochastic Systems, 10(1), 1-28
Stochastic Systems, 10(1), 1-28. INFORMS Institute for Operations Research and the Management Sciences

We consider the steady-state distribution of the sojourn time of a job entering an M/GI/1 queue with the foreground–background scheduling policy in heavy traffic. The growth rate of its mean as well as the limiting distribution are derived under br

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1545023966722073c7007df60bcf37d
https://research.tue.nl/en/publications/5df0404a-b1e9-447d-9598-7855695aa66c

Uniform asymptotics for compound Poisson processes with regularly varying jumps and vanishing drift

Autor: Bart Kamphorst, Bert Zwart

Publikováno v: Stochastic Processes and their Applications, 129(2), 572-603
Stochastic Processes and their Applications, 129(2), 572-603. Elsevier

This paper addresses heavy-tailed large deviation estimates for the distribution tail of functionals of a class of spectrally one-sided L\'evy process. Our contribution is to show that these estimates remain valid in a near-critical regime. This comp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f8e46c1fc684242b98109d7afbb39897
https://doi.org/10.1016/j.spa.2018.03.012

Achievable performance of blind policies in heavy traffic

Autor: Bart Kamphorst, Bert Zwart, Nikhil Bansal

Publikováno v: arXiv. Cornell University Library
arXiv
Mathematics of Operations Research, 43(3), 949-964. INFORMS Institute for Operations Research and the Management Sciences
Mathematics of Operations Research, 43(3), 949-964

For a GI/GI/1 queue, we show that the average sojourn time under the (blind) Randomized Multilevel Feedback algorithm is no worse than that under the Shortest Remaining Processing Time algorithm times a logarithmic function of the system load. Moreov

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14078bca69334eb68a4046bcfbcfe4b5
https://research.tue.nl/nl/publications/84699619-5d8d-4d09-ac1d-06e7ca8685c8