Last updated October 2024. For a PDF version, click here.
July 2018 - Oct 2018: Junior Researcher at BioSense Institute, University of Novi Sad, Novi Sad, Serbia
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.
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.
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.
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.
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.
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.
Armacki, A., Bajović, D., Jakovetić, D., & Kar, S. (2024). A Unified Framework for Gradient-based Clustering of Distributed Data. arxiv preprint, arxiv:2402.01302
Armacki, A., Yu, S., Sharma, P., Joshi, G., Bajović, D., Jakovetić, D., & Kar, S. (2024). Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees. arxiv preprint, arxiv:2410.13954.
Armacki, A., Yu, S., Bajović, D., Jakovetić, D., & Kar, S. (2024). Large Deviations and Improved Mean-squared Error Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry. arxiv preprint, arxiv:2410.15637
Armacki, A., Sharma, H., Bajović, D., Jakovetić, D., Chakraborty, M., & Kar, S. (2024). Distributed Gradient Clustering: Convergence and the Effect of Initialization. 58th Asilomar Conference on Signals, Systems, and Computers [To appear]