3 papers
stat.ML2026
No-Regret Gaussian Process Optimization of Time-Varying Functions
Eliabelle Mauduit, Eloïse Berthier, Andrea Simonetto
Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stat…
math.OC2026
No-regret optimization of time-varying bilevel problems
Eliabelle Mauduit, Eloïse Berthier, Andrea Simonetto
Bilevel optimization problems arise in many applications where decisions must account for the optimal response of another system, such as in game-theoretic settings. However, these…
math.OC2025
Time-varying Gaussian Process Bandit Optimization with Experts: no-regret in logarithmically-many side queries
Eliabelle Mauduit, Eloïse Berthier, Andrea Simonetto
We study a time-varying Bayesian optimization problem with bandit feedback, where the reward function belongs to a Reproducing Kernel Hilbert Space (RKHS). We approach the problem…