Summary
Please see personal website for details.
Stefan Vlaski is Lecturer in the Communications and Signal Processing Group within the Department of Electrical and Electronic Engineering, where he conducts research at the intersection of machine learning, network science and optimization with applications in signal processing and communications.
Stefan received the B.Sc. degree from Technical University Darmstadt, Germany, in 2013, and the M.S. as well as Ph.D. degree from the University of California, Los Angeles, USA, in 2014 and 2019, respectively. From 2019 to 2021 he was Postdoctoral Researcher with the Adaptive Systems Laboratory at École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland.
He was recipient of the German National Scholarship at TU Darmstadt and the Graduate Division Fellowship at UCLA. His papers have been recognized at Best Student Paper contests at IEEE ICASSP 2016 and IEEE CAMSAP 2019, and his research has led to patents which have been assigned to UCLA and Amazon.
Prospective Students
I am looking for driven students with a strong analytical interest to join our research team. Prospective students are encouraged to browse through recent publications, and if you feel our interests align, send me an email including CV and a short statement on research interests.
Selected Publications
Journal Articles
Kayaalp M, Vlaski S, Sayed A, 2022, Dif-MAML: Decentralized multi-agent meta-learning, Ieee Open Journal of Signal Processing, Vol:3, ISSN:2644-1322, Pages:71-93
Vlaski S, Sayed AH, 2021, Distributed learning in non-convex environments-Part II: polynomial escape from saddle-points, IEEE Transactions on Signal Processing, Vol:69, ISSN:1053-587X, Pages:1257-1270
Vlaski S, Sayed AH, 2021, Distributed learning in non-convex environments-Part I: agreement at a linear rate, IEEE Transactions on Signal Processing, Vol:69, ISSN:1053-587X, Pages:1242-1256
Nassif R, Vlaski S, Richard C, et al. , 2020, Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning, IEEE Signal Processing Magazine, Vol:37, ISSN:1053-5888, Pages:14-25