Autori: Jakovetic Dusan
| Naslov | Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization (Proceedings Paper) |
| Autori | Armacki Aleksandar Bajovic Dragana Jakovetic Dusan Kar Soummya Sayed Ali H |
| Info | THIRTY NINTH ANNUAL CONFERENCE ON LEARNING THEORY, (2026), vol. 336 br. , str. 337-370 |
| Projekat | NSF [2330196]; European Union's Horizon Europe Research and Innovation program [101135916]; Ministry of Science, Technological Development and Innovation of the Republic of Serbia [451-03-33/2026-03/200125, 451-03-34/2026-03/200125]; Science Fund of the Republic of Serbia [7359] |
| Ispravka | ISI/Web of Science Citati: |
| Naslov | Towards Automated Vulnerability Detection in Erlang Codebases Using Static Code Analysis (Proceedings Paper) |
| Autori | Kovacevic Vladimir Radovanovic Milos M Jakovetic Dusan Boberic-Krsticev Danijela |
| Info | ADVANCES IN ICT RESEARCH IN THE BALKANS, BCI 2025, (2026), vol. 2900 br. , str. 61-68 |
| Projekat | European Union's Horizon 2020 research and innovation programme [101120962] |
| Ispravka | ISI/Web of Science Članak Citati: |
| Naslov | Decentralized Intelligence in the Service of Heterogeneous Swarms (Proceedings Paper) |
| Autori | Bajovic Dragana Fodor Lidija Jakovetic Dusan Jankov Milica Komarica Stefan Petrovic Nemanja Simic Nikola B |
| Info | ADVANCES IN ICT RESEARCH IN THE BALKANS, BCI 2025, (2026), vol. 2900 br. , str. 16-23 |
| Projekat | European Union's Horizon Europe research and innovation program [101093006] |
| Ispravka | ISI/Web of Science Članak Citati: |
| Naslov | Distributed Gradient Methods Under Heavy-Tailed Communication Noise (Article) |
| Autori | Vukovic Manojlo Jakovetic Dusan Bajovic Dragana Kar Soummya |
| Info | IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS, (2026), vol. 13 br. 2, str. 761-772 |
| Projekat | Science Fund of the Republic of Serbia through Project LASCADO [7359]; Ministry of Science, Technological Development and Innovation [451-03-137/2025-03/200156]; Faculty of Technical Sciences, University of Novi Sad, through project "Scientific and Artistic Research Work of Researchers in Teaching and Associate Positions at the Faculty of Technical Sciences, University of Novi Sad 2025" [01-50/295]; Ministry of Science, Technological Development and Innovation of the Republic of Serbia [451-03-137/2025-03/200125, 451-03-136/2025-03/200125]; Provincial Secretariat for Higher Education and Scientific Research [142-451-2593/2021-01/2]; National Science Foundation [ECCS 2330196] |
| Ispravka | ISI/Web of Science Članak Elečas Rang časopisa Citati: |
| Naslov | Robust Federated Learning Under Adversarial Attacks via Loss-Based Client Clustering (Proceedings Paper) |
| Autori | Kritharakis Emmanouil Jakovetic Dusan Makris Antonios Tserpes Konstantinos |
| Info | MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2025, PT III, (2026), vol. 2841 br. , str. 508-523 |
| Projekat | European Union's Horizon Europe research and innovation actions [101168560]; European Union NextGenerationEU Recovery and Resilience Facility programme [16971, TAEDK-06199]; Ministry of Science, Technological Development and Innovation of the Republic of Serbia [451-03-137/2025-03/200125, 451-03-136/202503/200125]; Science Fund of the Republic of Serbia [7359] |
| Ispravka | ISI/Web of Science Članak |
| Naslov | The application of machine learning techniques to data from solid-state nuclear track detector CR-39 (Article; Early Access) |
| Autori | Vrban Branislav Vrtalova Vendula Knezevic Dusica Savic Milos Kurbalija Vladimir M Jakovetic Dusan Cerba Stefan Luley Jakub |
| Info | EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS, (2026), vol. br. , str. - |
| Projekat | HORIZON EUROPE Framework Programme [101135775]; Agentra na Podporu Vskumu a Vvoja [APVV-22-0304]; Recovery and Resilience Plan for Slovakia [09I01-03-V04-00098]; Slovak Technical University |
| Ispravka | ISI/Web of Science Članak Elečas Rang časopisa Citati: |
| Naslov | Smoothed Gradient Clipping and Error Feedback for Decentralized Optimization Under Symmetric Heavy-Tailed Noise (Article) |
| Autori | Yu Shuhua Jakovetic Dusan Kar Soummya |
| Info | SIAM JOURNAL ON OPTIMIZATION, (2026), vol. 36 br. 2, str. 703-728 |
| Projekat | NSF [ECCS 2330196]; Ministry of Science, Technological Development and Innovation, Republic of Serbia; Science Fund of Republic of Serbia [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 | 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 | Unlocking AIoT Efficiency in the Computing Continuum - the PANDORA framework (Proceedings Paper) |
| Autori | Bouloukakis Georgios Iosifidis Alexandros Kattepur Ajay Jakovetic Dusan Tserpes Konstantinos Pateraki Maria |
| Info | PROCEEDINGS OF THE 15TH INTERNATIONAL CONFERENCE ON THE INTERNET OF THINGS 2025, IOT 2025, (2025), vol. br. , str. 201-209 |
| Projekat | Horizon Europe project PANDORA [101135775] |
| Ispravka | ISI/Web of Science Članak Citati: ISI/Web of Science |
| Naslov | FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning (Proceedings Paper) |
| Autori | Kritharakis Emmanouil Makris Antonios Jakovetic Dusan Tserpes Konstantinos |
| Info | 2025 3RD INTERNATIONAL CONFERENCE ON FEDERATED LEARNING TECHNOLOGIES AND APPLICATIONS, FLTA, (2025), vol. br. , str. 348-355 |
| Projekat | European Union [101168560]; 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 the Republic of Serbia, project LASCADO [7359] |
| Ispravka | ISI/Web of Science Članak Citati: ISI/Web of Science |
