Nicolò Cesa-Bianchi

Adversarial bandits with $m$-set choices can suffer drastically slower learning rates than previously thought, with regret scaling quadratically with $m$ in some settings.

The query complexity of active learning algorithms can be dramatically influenced by the graph's vertex expansion, revealing a new dimension in adversarial robustness.

Gradient variation, not just magnitude, unlocks tighter regret bounds in online learning, even without knowing problem parameters.

Unconstrained bandit linear optimization can be surprisingly reduced to standard online linear optimization using a perturbation approach, unlocking new regret guarantees and high-probability bounds.