3 papers
math.OC2025
Two-Stage Data-Driven Contextual Robust Optimization: An End-to-End Learning Approach for Online Energy Applications
Carlos Gamboa, Alexandre Street, Davi Valladão +1
Traditional end-to-end contextual robust optimization models are trained for specific contextual data, requiring complete retraining whenever new contextual information arrives. Th…
eess.SY2025
Assessing the Optimistic Bias in the Natural Inflow Forecasts: A Call for Model Monitoring in Brazil
Arthur Brigatto, Alexandre Street, Cristiano Fernandes +3
Hydroelectricity accounted for roughly 61.4% of Brazil's total generation in 2024 and addressed most of the intermittency of wind and solar generation. Thus, inflow forecasting pla…
cs.LG2025
Efficiently Training Deep-Learning Parametric Policies using Lagrangian Duality
Andrew Rosemberg, Alexandre Street, Davi M. Valladão +1
Constrained Markov Decision Processes (CMDPs) are critical in many high-stakes applications, where decisions must optimize cumulative rewards while strictly adhering to complex non…