Asosiy kontentga oʻtish
Maqola

SwarmPNM: A Single-Trajectory Adaptive Optimizer with Positive–Negative Momentum and PSO-Inspired Attraction

Ruslan I. AbdulkadirovNorth-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355017 Stavropol, RussiaNodir RabimovDepartment of Artificial Intelligence and Information Systems, Samarkand State University, Samarkand 140104, UzbekistanAdam AlikhanovNorth-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355017 Stavropol, RussiaNabi AydamirovNorth-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355017 Stavropol, RussiaRobert BabayanNorth-Caucasus Center for Mathematical Research, North-Caucasus Federal University, 355017 Stavropol, RussiaRuslan KhairbekovDepartment of Mathematical Modelling, North-Caucasus Federal University, 355009 Stavropol, RussiaNikolay Nikolaevich NagornovDepartment of Mathematical Modelling, North-Caucasus Federal University, 355009 Stavropol, RussiaPavel LyakhovDepartment of Mathematical Modelling, North-Caucasus Federal University, 355009 Stavropol, RussiaА. И. ВорошиловаSchool of Public Administration and Entrepreneurship, Graduate School of Economics and Management, Ural Federal University Named After the First President of Russia B.N. Yeltsin, 19 Mira Street, 620002 Ekaterinburg, RussiaEkaterina E. KopetsYouth Research Institute, Saint-Petersburg Electrotechnical University “LETI”, Professora Popova St. 5, 197022 Saint-Petersburg, RussiaКалита Диана ИвановнаDepartment of Mathematical Modelling, North-Caucasus Federal University, 355009 Stavropol, Russia
2026en
Ochiq kirishOltin

Litsenziya: cc-by

ABI

Annotatsiya

SwarmPNM combines an adaptive second-moment estimate and positive–negative gradient momentum with attraction towards the lowest-loss weights stored along a single training trajectory. The attraction is inspired by particle swarm optimization, but the method does not maintain a particle population. We specify the update, analyze the attraction locally under Hessian assumptions and obtain a conditional regret bound for an auxiliary strongly convex projected-gradient model with controlled perturbations. Experiments cover 15 analytic test functions, molecular classification with MolCLR-pretrained GIN and GCN encoders on the blood–brain barrier penetration (BBBP), beta-secretase-1 inhibitor (BACE) and human immunodeficiency virus replication-inhibition (HIV) datasets, and nuclear cross-section regression with a multilayer perceptron. SwarmPNM attains the highest mean ROC–AUC in five of six molecular dataset–encoder combinations. In the four-library nuclear comparison, it has the lowest mean absolute error and the highest coefficient of determination; a separate three-seed nuclear experiment under a different protocol favors AdamW. Repeated-run, sensitivity and ablation studies establish that the contribution of attraction depends on the task and tuning, with the learning rate having the largest observed influence in the analytic sensitivity tests. We also report the additional computational cost relative to AdamW. The auxiliary theory does not establish convergence of the complete nonconvex optimizer.

Hali tarjima qilinmagan

Identifikatorlar

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba