Last updated Dec 2023. For a PDF version, click here.

Education

• Ph.D in Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA, 2020 - present
• M.Sc. in Applied Mathematics, Faculty of Sciences, University of Novi Sad, Novi Sad, Serbia, 2018
• B.Sc. in Applied Mathematics, Faculty of Sciences, University of Novi Sad, Novi Sad, Serbia, 2016

Experience

• Aug 2020 - present: Research Assistant at Carnegie Mellon University, Pittsburgh, PA, USA
  • Advisor: Prof. Soummya Kar
• Nov 2018 - Jun 2020: Junior Researcher at Faculty of Sciences, University of Novi Sad, Novi Sad, Serbia
  • Advisor: Prof. Dušan Jakovetić
• Sep 2019 - Dec 2019: Visiting Researcher at University of Pennsylvania, Philadelphia, PA, USA
  • Advisor: Prof. Alejandro Ribeiro

• July 2018 - Oct 2018: Junior Researcher at BioSense Institute, University of Novi Sad, Novi Sad, Serbia

• Feb 2018 - July 2018: Visiting Researcher at Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia
  • Advisor: Prof. Blaž Zupan

Publications

Distributed Trust-region Method with First Order Models

A. Armacki, D. Jakovetić, N. Krejić and N. K. Jerinkić, "Distributed Trust-Region Method With First Order Models," IEEE EUROCON 2019 -18th International Conference on Smart Technologies, Novi Sad, Serbia, 2019, pp. 1-6, doi: 10.1109/EUROCON.2019.8861739.

Gradient Based Clustering

Armacki, A., Bajović, D., Jakovetić, D. & Kar, S. (2022). Gradient Based Clustering. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:929-947.

Personalized Federated Learning via Convex Clustering

A. Armacki, D. Bajović, D. Jakovetić and S. Kar, "Personalized Federated Learning via Convex Clustering," 2022 IEEE International Smart Cities Conference (ISC2), Pafos, Cyprus, 2022, pp. 1-7, doi: 10.1109/ISC255366.2022.9921863.

Communication Efficient Model-aware Federated Learning for Visual Crowd Counting and Density Estimation in Smart Cities

Armacki, A., Milošević, N., Bajović, D., Kar, S., Jakovetić, D., Bakhtiarnia, A., Esterle, L., Muscat, A., & Festi, T. (2023). Communication Efficient Model-aware Federated Learning for Visual Crowd Counting and Density Estimation in Smart Cities. EUSIPCO 2023 31st European Signal Processing Conference, Helsinki, Finland.

High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise

Armacki, A., Sharma, P., Joshi, G., Bajović, D., Jakovetić, D., & Kar, S. (2023). High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise. arxiv preprint, arxiv:2310.18784.

A One-shot Framework for Distributed Clustered Learning in Heterogeneous Environments

Armacki, A., Bajović, D., Jakovetić, D., & Kar, S. "A One-Shot Framework for Distributed Clustered Learning in Heterogeneous Environments," in IEEE Transactions on Signal Processing, vol. 72, pp. 636-651, 2024, doi: 10.1109/TSP.2023.3343561.

A Unified Framework for Gradient-based Clustering of Distributed Data

Armacki, A., Bajović, D., Jakovetić, D., & Kar, S. (2024). A Unified Framework for Gradient-based Clustering of Distributed Data. arxiv preprint, arxiv:2402.01302

Awards

• IBM PhD Fellowship - Finalist. One of three nominees by the Electrical and Computer Engineering Department, Carnegie Mellon University, 2023
• Dean’s Fellowship - Department of Electrical and Computer Engineering, Carnegie Mellon University, 2020
• Annual Award of the Mathematical Institute of the Serbian Academy of Sciences and Arts for M.Sc. Students in the Field of Computing - Finalist, 2019
• Various government awards and fellowships for students with stellar academic record - Serbia, 2012-18

Teaching

Linear Systems - Fall 2022

Linear Systems - Fall 2023

Academic Service

• Reviewing:
  • AISTATS - 2023, 2024
• Carnegie Mellon University:
  • Electrical and Computer Engineering Department Student Council for Faculty Hiring - 2023