Digital twinIndustrial AI and digital twins could help Vietnam escape assembly trapBáo VietNamNet · 23hDigital twinЦифровые двойники (Digital Twin) в инженерных системах — Часть 1. Управление документациейХабр · yesterdayDigital twinIndustrial AI and digital twins as Vietnam's path to technological self-relianceVietnam.vn · yesterdayDigital twinDigital twins should be built for valueAVEVA · yesterdayModellingSafe reinforcement learning combined with MPC and control barrier functionsarXiv — Systems and Control (eess.SY) · yesterdayModellingRAZeR: Representation Aware Zonotope ReductionarXiv — Systems and Control (eess.SY) · yesterdayModellingВ России создали мультиагентную систему «Радар» для автоматизации закупочных процессовCNews · yesterdayModelling«Думейт» вывела агентное приложение из беты: российская альтернатива Claude CodeCNews · yesterdayDigital twinMode switches in cyber-physical systems leak sensitive events through timingarXiv — Systems and Control (eess.SY) · yesterdayDigital twinDigital twins of respondents distilled from survey histories into compact personasarXiv — Computers and Society (cs.CY) · yesterdayEnergyRussian pipeline gas deliveries to Turkey down 18% over nine monthsТАСС · yesterdayDigital twinStochastic closure models learned without direct closure dataarXiv API — полнотекстовый поиск "digital twin" · 2d
Bayesian inference for agent-based models with 90% fewer simulations
US & West ·
The DF-NPE method combines learned time-series summaries with two conditional normalizing flows for synthetic-data generation and posterior estimation. It supplements direct simulations with synthetic training pairs and supports pooled and ordered training strategies. In two settings of the Brock-Hommes asset-pricing model it cuts direct simulations by 90% while achieving lower posterior discrepancy and runtime.
Why it matters
It lowers the computational cost of calibrating agent-based models, making them more practical for forecasting and scenario analysis in economics.
The PECTS framework learns stochastic system dynamics with probabilistic neural networks and control barrier functions with Lipschitz-bounded networks. Learned barrier constraints are embedded in a model predictive control formulation that accounts for model uncertainty. This provides probabilistic safety when learning under unknown and stochastic dynamics.
arXiv:2611.17479v1 Announce Type: new Abstract: Reachability analysis is a popular technique for verifying the safety of a dynamical system under uncertainty, where the uncertainty is often represented by zonotopes.