Claudia Soares — accepted AI-conference papers

2026

CLASP: Online learning algorithms for Convex Losses And Squared Penalties

Ricardo N. Ferreira, Joao Xavier, Claudia Soares

ICML 2026poster

Addressing Constrained Online Convex Optimization (COCO), we introduce CLASP (Convex Losses And Squared Penalties), a framework that minimizes cumulative loss together with squared constraint violations. We propose two variants of CLASP, CLASP-I and CLASP-F, allowing for a joint or separate handling…

Cited by 0 Source ↗Scholar ↗

2025

OrbitZoo: Real Orbital Systems Challenges for Reinforcement Learning

Alexandre Oliveira, Katarina Dyreby, Francisco Miguel Caldas, Claudia Soares

NeurIPS 2025poster

The increasing number of satellites and orbital debris has made space congestion a critical issue, threatening satellite safety and sustainability. Challenges such as collision avoidance, station-keeping, and orbital maneuvering require advanced techniques to handle dynamic uncertainties and multi-a…

Cited by 0 Source ↗Scholar ↗