Autori: Armacki Aleksandar
| Naslov | Large Deviation Upper Bounds and Improved Mse Rates of Nonlinear Sgd: Heavy-Tailed Noise and Power of Symmetry (Article) |
| Autori | Armacki Aleksandar Yu Shuhua Bajovic Dragana Jakovetic Dusan Kar Soummya |
| Info | SIAM JOURNAL ON OPTIMIZATION, (2026), vol. 36 br. 1, str. 32-59 |
| Projekat | National Science Foundation [ECCS 2330196]; Ministry of Science, Technological Development, and Innovation [451-03-65/2024-03/200156]; Faculty of Technical Sciences, University of Novi Sad [01-3394/1]; Ministry of Science, Technological Development, and Innovation of the Republic of Serbia [451-03-137/2025-03/200125, 451-03-136/2025-03/200125]; Science Fund of Republic of Serbia, project "LASCADO" [7359]; Provincial Secretariat for Higher Education and Scientific Research [142-451-2593/2021-01/2] |
| Ispravka | ISI/Web of Science Članak Elečas Rang časopisa |
| Naslov | High-probability Convergence Bounds for Online Nonlinear Stochastic Gradient Descent under Heavy-tailed Noise (Proceedings Paper) |
| Autori | Armacki Aleksandar Yu Shuhua Sharma Pranay Joshi Gauri Bajovic Dragana Jakovetic Dusan Kar Soummya |
| Info | INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, (2025), vol. 258 br. , str. - |
| Projekat | NSF [CCF 2045694, CNS-2112471, CPS-2111751, SHF-2107024, ECCS-2330196]; ONR [N00014-23-1-2149]; Ministry of Science, Technological Development and Innovation [451-03-65/2024-03/200156]; Faculty of Technical Sciences, University of Novi Sad [01-3394/1]; European Union's Horizon Europe program [101093006, 101135775, 101135916]; Science Fund of Republic of Serbia, project "LASCADO" [7359]; Provincial Secretariat for Higher Education and Scientific Research [142-451-2593/2021-01/2] |
| Ispravka | ISI/Web of Science |
| Naslov | Distributed Center-Based Clustering: A Unified Framework (Article) |
| Autori | Armacki Aleksandar Bajovic Dragana Jakovetic Dusan Kar Soummya |
| Info | IEEE TRANSACTIONS ON SIGNAL PROCESSING, (2025), vol. 73 br. , str. 903-918 |
| Projekat | National Science Foundation [ECCS 2330195]; Ministry of Science, Technological Development and Innovation [451-03-65/2024-03/200156]; Faculty of Technical Sciences, University of Novi Sad [01-3394/1]; Serbian Ministry of Science, Technological development and Innovation [337-00-3/2024-05/16]; Science Fund of Republic of Serbia, project "LASCADO" [7359]; Provincial Secretariat for Higher Education and Scientific Research, [142-451-2593/2021-01/2]; European Union [101093006] |
| Ispravka | ISI/Web of Science Članak Elečas Rang časopisa |
| Naslov | Distributed Gradient Clustering: Convergence and the Effect of Initialization (Proceedings Paper) |
| Autori | Armacki Aleksandar Sharma Himkant Bajovic Dragana Jakovetic Dusan Chakraborty Mrityunjoy Kar Soummya |
| Info | 2024 58TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, (2024), vol. br. , str. 1461-1465 |
| Projekat | National Science Foundation [ECCS 2330196]; SPARC grant from the MHRD, Govt. of India; Ministry of Science, Technological Development and Innovation [451-03-65/2024-03/200156]; Faculty of Technical Sciences, University of Novi Sad [01-3394/1]; Serbian Ministry of Science, Technological development and Innovation, within the bilateral project Serbia-Slovakia [337-00-3/2024-05/16]; Science Fund of Republic of Serbia, project "LASCADO" [7359]; Provincial Secretariat for Higher Education and Scientific Research [142-451-2593/2021-01/2]; European Union's Horizon Europe program [101093006] |
| Ispravka | ISI/Web of Science Članak |
| Naslov | A One-Shot Framework for Distributed Clustered Learning in Heterogeneous Environments (Article) |
| Autori | Armacki Aleksandar Bajovic Dragana Jakovetic Dusan Kar Soummya |
| Info | IEEE TRANSACTIONS ON SIGNAL PROCESSING, (2024), vol. 72 br. , str. 636-651 |
| Projekat | Office of Naval Research |
| Ispravka | ISI/Web of Science Članak Elečas Rang časopisa |
| Naslov | Gradient Based Clustering (Proceedings Paper) |
| Autori | Armacki Aleksandar Bajovic Dragana Jakovetic Dusan Kar Soummya |
| Info | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, (2022), vol. br. , str. 929-947 |
| Projekat | National Science Foundation [CNS-1837607]; European Union [957337, 871518] |
| Ispravka | ISI/Web of Science |
| Naslov | Distributed Trust-Region Method With First Order Models (Proceedings Paper) |
| Autori | Armacki Aleksandar Jakovetic Dusan Krejic Natasa Krklec-Jerinkic Natasa |
| Info | PROCEEDINGS OF 18TH INTERNATIONAL CONFERENCE ON SMART TECHNOLOGIES (IEEE EUROCON 2019), (2019), vol. br. , str. - |
| Projekat | Serbian Ministry of Education, Science, and Technological Development [174030]; European Commission Joint Research Centre [780787] |
| Ispravka | ISI/Web of Science Citati: ISI/Web of Science Scopus |
