Bandit convex optimisation

T Lattimore - arXiv preprint arXiv:2402.06535, 2024 - arxiv.org
Bandit convex optimisation is a fundamental framework for studying zeroth-order convex
optimisation. These notes cover the many tools used for this problem, including cutting plane …

Adaptive maximization of social welfare

N Cesa-Bianchi, R Colomboni, M Kasy - arXiv preprint arXiv:2310.09597, 2023 - arxiv.org
We consider the problem of repeatedly choosing policies to maximize social welfare.
Welfare is a weighted sum of private utility and public revenue. Earlier outcomes inform later …

Online Learning Methods for Digital Markets

R Colomboni - 2024 - air.unimi.it
We cast several problems arising from digital markets and economics into an online learning
framework, where a learner sequentially interacts with an unknown environment, trying to …