Aleksandar Armacki

According to our database, Aleksandar Armacki authored at least 19 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

High-Probability Convergence in Decentralized Stochastic Optimization with Gradient Tracking.

Aleksandar Armacki, Haoyuan Cai, Ali H. Sayed

CoRR, May, 2026

Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar, Ali H. Sayed

CoRR, February, 2026

Large Deviation Upper Bounds and Improved MSE Rates of Nonlinear SGD: Heavy-Tailed Noise and Power of Symmetry.

Aleksandar Armacki, Shuhua Yu, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

SIAM J. Optim., 2026

2025

Improved High-probability Convergence Guarantees of Decentralized SGD.

Aleksandar Armacki, Ali H. Sayed

CoRR, October, 2025

Optimal High-probability Convergence of Nonlinear SGD under Heavy-tailed Noise via Symmetrization.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, July, 2025

Distributed Center-Based Clustering: A Unified Framework.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

IEEE Trans. Signal Process., 2025

Toward Understanding the Improved Robustness to Initialization in Distributed Clustering.

Aleksandar Armacki, Soummya Kar

Proceedings of the 33rd European Signal Processing Conference, 2025

High-probability Convergence Bounds for Online Nonlinear Stochastic Gradient Descent under Heavy-tailed Noise.

Aleksandar Armacki, Shuhua Yu, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

A One-Shot Framework for Distributed Clustered Learning in Heterogeneous Environments.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

IEEE Trans. Signal Process., 2024

Large Deviations and Improved Mean-squared Error Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry.

Aleksandar Armacki, Shuhua Yu, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, 2024

Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees.

Aleksandar Armacki, Shuhua Yu, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, 2024

A Unified Framework for Gradient-based Clustering of Distributed Data.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, 2024

Distributed Gradient Clustering: Convergence and the Effect of Initialization.

Aleksandar Armacki, Himkant Sharma, Dragana Bajovic, Dusan Jakovetic, Mrityunjoy Chakraborty, Soummya Kar

Proceedings of the 58th Asilomar Conference on Signals, 2024

2023

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

Aleksandar Armacki, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, 2023

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

Aleksandar Armacki, Nemanja Milosevic, Dragana Bajovic, Soummya Kar, Dusan Jakovetic, Arian Bakhtiarnia, Lukas Esterle, Adrian Muscat, Thomas Festi

Proceedings of the 31st European Signal Processing Conference, 2023

2022

One-Shot Federated Learning for Model Clustering and Learning in Heterogeneous Environments.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

CoRR, 2022

Personalized Federated Learning via Convex Clustering.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

Proceedings of the IEEE International Smart Cities Conference, 2022

Gradient Based Clustering.

Aleksandar Armacki, Dragana Bajovic, Dusan Jakovetic, Soummya Kar

Proceedings of the International Conference on Machine Learning, 2022

2019

Distributed Trust-Region Method With First Order Models.

Aleksandar Armacki, Dusan Jakovetic, Natasa Krejic, Natasa Krklec Jerinkic

Proceedings of the IEEE EUROCON 2019, 2019